1 | Near-Optimal No-Regret Learning in General Games | 8.75 | 0.83 | 9, 10, 8, 8 | Oral | Oral | |

2 | Volume Rendering of Neural Implicit Surfaces | 8.50 | 0.87 | 9, 9, 7, 9 | Oral | Oral | |

3 | Hessian Eigenspectra of More Realistic Nonlinear Models | 8.50 | 0.50 | 9, 8, 9, 8 | Oral | Oral | |

4 | Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions | 8.33 | 0.47 | 9, 8, 8 | Oral | Oral | |

5 | List-Decodable Mean Estimation in Nearly-PCA Time | 8.33 | 1.25 | 8, 10, 7 | Spotlight | Spotlight | |

6 | Learning with Noisy Correspondence for Cross-modal Matching | 8.25 | 0.83 | 7, 8, 9, 9 | Oral | Oral | |

7 | Interesting Object, Curious Agent: Learning Task-Agnostic Exploration | 8.25 | 0.43 | 9, 8, 8, 8 | Oral | Oral | |

8 | DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras | 8.25 | 0.83 | 9, 7, 9, 8 | Oral | Oral | |

9 | Learning Treatment Effects in Panels with General Intervention Patterns | 8.25 | 1.30 | 7, 7, 10, 9 | Oral | Oral | |

10 | Shape As Points: A Differentiable Poisson Solver | 8.25 | 0.43 | 8, 9, 8, 8 | Oral | Oral | |

11 | Alias-Free Generative Adversarial Networks | 8.25 | 1.48 | 6, 10, 9, 8 | Oral | Oral | |

12 | Coresets for Clustering with Missing Values | 8.25 | 0.43 | 9, 8, 8, 8 | Spotlight | Spotlight | |

13 | Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons | 8.00 | 0.71 | 9, 8, 7, 8 | Oral | Oral | ✔ |

14 | MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers | 8.00 | 0.00 | 8, 8, 8, 8 | Oral | Oral | |

15 | An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap | 8.00 | 0.00 | 8, 8, 8, 8 | Oral | Oral | |

16 | Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification | 8.00 | 0.71 | 8, 7, 9, 8 | Oral | Oral | ✔ |

17 | Attention over Learned Object Embeddings Enables Complex Visual Reasoning | 8.00 | 0.71 | 8, 9, 8, 7 | Oral | Oral | |

18 | Oracle Complexity in Nonsmooth Nonconvex Optimization | 8.00 | 0.63 | 8, 7, 8, 8, 9 | Oral | Oral | |

19 | Differentiable Annealed Importance Sampling and the Perils of Gradient Noise | 8.00 | 0.82 | 7, 9, 8 | Poster | Poster | |

20 | IQ-Learn: Inverse soft-Q Learning for Imitation | 8.00 | 0.71 | 7, 8, 9, 8 | Spotlight | Spotlight | |

21 | Aligned Structured Sparsity Learning for Efficient Image Super-Resolution | 8.00 | 0.00 | 8, 8, 8 | Spotlight | Spotlight | ✔ |

22 | Credit Assignment in Neural Networks through Deep Feedback Control | 8.00 | 0.82 | 9, 7, 8 | Spotlight | Spotlight | |

23 | Learning Frequency Domain Approximation for Binary Neural Networks | 7.75 | 0.43 | 7, 8, 8, 8 | Oral | Oral | ✔ |

24 | On the Expressivity of Markov Reward | 7.75 | 0.43 | 7, 8, 8, 8 | Oral | Oral | |

25 | Deep Reinforcement Learning at the Edge of the Statistical Precipice | 7.75 | 0.83 | 7, 8, 7, 9 | Oral | Oral | |

26 | A Universal Law of Robustness via Isoperimetry | 7.75 | 1.48 | 7, 6, 8, 10 | Oral | Oral | |

27 | Online Variational Filtering and Parameter Learning | 7.75 | 0.43 | 8, 7, 8, 8 | Oral | Oral | |

28 | Associating Objects with Transformers for Video Object Segmentation | 7.75 | 0.43 | 8, 8, 7, 8 | Poster | Poster | |

29 | Cortico-cerebellar networks as decoupling neural interfaces | 7.75 | 0.43 | 8, 8, 7, 8 | Poster | Poster | |

30 | Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems | 7.75 | 0.43 | 7, 8, 8, 8 | Spotlight | Spotlight | ✔ |

31 | What’s a good imputation to predict with missing values? | 7.75 | 0.83 | 7, 9, 8, 7 | Spotlight | Spotlight | |

32 | Self-Supervised Learning Disentangled Group Representation as Feature | 7.75 | 0.83 | 7, 9, 7, 8 | Spotlight | Spotlight | |

33 | Learning Equilibria in Matching Markets from Bandit Feedback | 7.75 | 0.83 | 7, 9, 8, 7 | Spotlight | Spotlight | |

34 | Combiner: Full Attention Transformer with Sparse Computation Cost | 7.75 | 0.83 | 8, 9, 7, 7 | Spotlight | Spotlight | |

35 | NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction | 7.75 | 0.43 | 7, 8, 8, 8 | Spotlight | Spotlight | |

36 | Statistical Query Lower Bounds for List-Decodable Linear Regression | 7.75 | 0.43 | 8, 8, 8, 7 | Spotlight | Spotlight | ✔ |

37 | On the Representation of Solutions to Elliptic PDEs in Barron Spaces | 7.75 | 1.30 | 9, 7, 6, 9 | Spotlight | Spotlight | |

38 | Offline RL Without Off-Policy Evaluation | 7.75 | 0.83 | 8, 9, 7, 7 | Spotlight | Spotlight | ✔ |

39 | A sampling-based circuit for optimal decision making | 7.75 | 0.43 | 8, 8, 7, 8 | Spotlight | Spotlight | |

40 | Beyond Tikhonov: faster learning with self-concordant losses, via iterative regularization | 7.75 | 0.43 | 7, 8, 8, 8 | Spotlight | Spotlight | ✔ |

41 | Aligning Pretraining for Detection via Object-Level Contrastive Learning | 7.75 | 0.83 | 9, 8, 7, 7 | Spotlight | Spotlight | |

42 | Learning to Draw: Emergent Communication through Sketching | 7.67 | 0.47 | 8, 8, 7 | Oral | Oral | |

43 | Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting | 7.67 | 0.47 | 7, 8, 8 | Oral | Oral | |

44 | Unsupervised Speech Recognition | 7.67 | 0.47 | 8, 8, 7 | Oral | Oral | |

45 | Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning | 7.67 | 0.47 | 8, 8, 7 | Poster | Poster | |

46 | Backward-Compatible Prediction Updates: A Probabilistic Approach | 7.67 | 0.47 | 8, 8, 7 | Poster | Poster | |

47 | Early Convolutions Help Transformers See Better | 7.67 | 0.94 | 7, 9, 7 | Poster | Poster | |

48 | Towards a Unified Information-Theoretic Framework for Generalization | 7.67 | 1.25 | 9, 6, 8 | Spotlight | Spotlight | |

49 | Probabilistic Tensor Decomposition of Neural Population Spiking Activity | 7.67 | 0.47 | 7, 8, 8 | Spotlight | Spotlight | |

50 | Unintended Selection: Persistent Qualification Rate Disparities and Interventions | 7.67 | 1.25 | 8, 9, 6 | Spotlight | Spotlight | |

51 | Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning | 7.67 | 0.47 | 7, 8, 8 | Spotlight | Spotlight | |

52 | MCMC Variational Inference via Uncorrected Hamiltonian Annealing | 7.60 | 0.49 | 7, 7, 8, 8, 8 | Poster | Poster | |

53 | Bellman-consistent Pessimism for Offline Reinforcement Learning | 7.50 | 0.50 | 8, 8, 7, 7 | Oral | Oral | |

54 | Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss | 7.50 | 0.50 | 7, 8, 8, 7 | Oral | Oral | |

55 | Stability and Deviation Optimal Risk Bounds with Convergence Rate
O(1/n) | 7.50 | 0.87 | 7, 9, 7, 7 | Oral | Oral | |

56 | Differentiable Quality Diversity | 7.50 | 0.50 | 7, 7, 8, 8 | Oral | Oral | |

57 | Partial success in closing the gap between human and machine vision | 7.50 | 1.12 | 9, 6, 8, 7 | Oral | Oral | |

58 | Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms | 7.50 | 0.87 | 7, 7, 9, 7 | Oral | Oral | |

59 | Retiring Adult: New Datasets for Fair Machine Learning | 7.50 | 0.50 | 7, 8, 8, 7 | Oral | Oral | |

60 | The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition | 7.50 | 0.50 | 7, 8, 8, 7 | Oral | Oral | |

61 | Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks | 7.50 | 0.50 | 7, 8, 8, 7 | Poster | Poster | |

62 | Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning | 7.50 | 1.12 | 7, 8, 6, 9 | Poster | Poster | |

63 | Making a (Counterfactual) Difference One Rationale at a Time | 7.50 | 0.50 | 8, 7, 7, 8 | Poster | Poster | |

64 | Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning | 7.50 | 0.50 | 7, 8, 7, 8 | Poster | Poster | |

65 | Information Directed Reward Learning for Reinforcement Learning | 7.50 | 1.12 | 6, 9, 8, 7 | Poster | Poster | |

66 | Optimal prediction of Markov chains with and without spectral gap | 7.50 | 0.87 | 7, 7, 7, 9 | Poster | Poster | |

67 | SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization | 7.50 | 1.12 | 7, 6, 9, 8 | Poster | Poster | ✔ |

68 | Coresets for Classification – Simplified and Strengthened | 7.50 | 0.50 | 7, 8, 8, 7 | Poster | Poster | |

69 | Universal Rate-Distortion-Perception Representations for Lossy Compression | 7.50 | 0.50 | 8, 7, 8, 7 | Poster | Poster | |

70 | STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data | 7.50 | 1.12 | 9, 8, 6, 7 | Poster | Poster | ✔ |

71 | Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning | 7.50 | 0.50 | 8, 8, 7, 7 | Poster | Poster | |

72 | Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism | 7.50 | 0.87 | 8, 6, 8, 8 | Poster | Poster | |

73 | Non-asymptotic convergence bounds for Wasserstein approximation using point clouds | 7.50 | 1.12 | 7, 6, 8, 9 | Poster | Spotlight | ✔ |

74 | Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization | 7.50 | 1.12 | 6, 8, 7, 9 | Poster | Poster | |

75 | Emergent Discrete Communication in Semantic Spaces | 7.50 | 0.50 | 8, 7, 8, 7 | Poster | Poster | ✔ |

76 | Localization with Sampling-Argmax | 7.50 | 0.87 | 7, 7, 7, 9 | Poster | Poster | ✔ |

77 | Heavy Ball Momentum for Conditional Gradient | 7.50 | 0.50 | 8, 8, 7, 7 | Poster | Poster | |

78 | Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling | 7.50 | 0.87 | 8, 8, 6, 8 | Spotlight | Spotlight | |

79 | Neural Program Generation Modulo Static Analysis | 7.50 | 1.12 | 8, 6, 7, 9 | Spotlight | Spotlight | |

80 | Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience | 7.50 | 0.50 | 8, 7, 7, 8 | Spotlight | Spotlight | |

81 | DiBS: Differentiable Bayesian Structure Learning | 7.50 | 0.50 | 8, 7, 7, 8 | Spotlight | Spotlight | |

82 | Habitat 2.0: Training Home Assistants to Rearrange their Habitat | 7.50 | 1.66 | 8, 10, 6, 6 | Spotlight | Spotlight | |

83 | Sequence-to-Sequence Learning with Latent Neural Grammars | 7.50 | 0.87 | 9, 7, 7, 7 | Spotlight | Spotlight | ✔ |

84 | Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering | 7.50 | 0.50 | 8, 7, 7, 8 | Spotlight | Spotlight | |

85 | Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and Learning | 7.50 | 0.50 | 7, 7, 8, 8 | Spotlight | Spotlight | |

86 | MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge | 7.50 | 0.50 | 7, 8, 7, 8 | Spotlight | Spotlight | |

87 | Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering | 7.50 | 0.50 | 8, 7, 7, 8 | Spotlight | Spotlight | |

88 | A Normative and Biologically Plausible Algorithm for Independent Component Analysis | 7.50 | 0.50 | 8, 7, 7, 7, 8, 8 | Spotlight | Spotlight | |

89 | Bayesian Bellman Operators | 7.50 | 0.50 | 7, 7, 8, 8 | Spotlight | Spotlight | |

90 | Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval | 7.50 | 0.50 | 8, 7, 7, 8 | Spotlight | Spotlight | |

91 | Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret | 7.50 | 0.50 | 8, 8, 7, 7 | Spotlight | Spotlight | |

92 | Hash Layers For Large Sparse Models | 7.50 | 0.87 | 7, 7, 7, 9 | Spotlight | Spotlight | |

93 | Statistical Query Lower Bounds for List-Decodable Linear Regression | 7.50 | 0.50 | 8, 8, 7, 7 | Spotlight | Spotlight | ✔ |

94 | A Geometric Analysis of Neural Collapse with Unconstrained Features | 7.50 | 0.50 | 8, 8, 7, 7 | Spotlight | Spotlight | |

95 | Covariance-Aware Private Mean Estimation Without Private Covariance Estimation | 7.50 | 0.50 | 7, 8, 8, 7 | Spotlight | Spotlight | |

96 | A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms | 7.50 | 0.87 | 7, 7, 9, 7 | Spotlight | Spotlight | |

97 | Littlestone Classes are Privately Online Learnable | 7.50 | 0.50 | 8, 7, 8, 7 | Spotlight | Spotlight | |

98 | Numerical Composition of Differential Privacy | 7.50 | 1.12 | 6, 8, 9, 7 | Spotlight | Spotlight | |

99 | Explaining Latent Representations with a Corpus of Examples | 7.50 | 0.50 | 8, 7, 7, 8 | Spotlight | Spotlight | |

100 | Conformal Prediction using Conditional Histograms | 7.50 | 0.76 | 7, 8, 7, 7, 7, 9 | Spotlight | Spotlight | |

101 | ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning | 7.50 | 1.12 | 8, 9, 6, 7 | Spotlight | Spotlight | |

102 | Correlated Stochastic Block Models: Exact Graph Matching with Applications to Recovering Communities | 7.50 | 0.50 | 8, 8, 7, 7 | Spotlight | Spotlight | |

103 | Diffusion Models Beat GANs on Image Synthesis | 7.50 | 1.12 | 9, 8, 7, 6 | Spotlight | Spotlight | ✔ |

104 | Diffusion Models Beat GANs on Image Synthesis | 7.50 | 0.87 | 9, 7, 7, 7 | Spotlight | Spotlight | ✔ |

105 | A Unified Approach to Fair Online Learning via Blackwell Approachability | 7.50 | 0.87 | 7, 9, 7, 7 | Spotlight | Spotlight | |

106 | Optimal Policies Tend To Seek Power | 7.50 | 0.50 | 7, 8, 8, 7 | Spotlight | Spotlight | |

107 | Private learning implies quantum stability | 7.50 | 0.50 | 8, 8, 7, 7 | Spotlight | Spotlight | |

108 | Sequential Causal Imitation Learning with Unobserved Confounders | 7.40 | 0.80 | 9, 7, 7, 7, 7 | Oral | Oral | ✔ |

109 | Moser Flow: Divergence-based Generative Modeling on Manifolds | 7.40 | 0.49 | 7, 8, 8, 7, 7 | Oral | Oral | |

110 | Estimating Multi-cause Treatment Effects via Single-cause Perturbation | 7.40 | 1.02 | 7, 7, 9, 8, 6 | Poster | Poster | |

111 | iFlow: Numerically Invertible Flows for Efficient Lossless Compression via a Uniform Coder | 7.40 | 1.20 | 8, 8, 6, 9, 6 | Spotlight | Spotlight | |

112 | Align before Fuse: Vision and Language Representation Learning with Momentum Distillation | 7.40 | 0.80 | 9, 7, 7, 7, 7 | Spotlight | Spotlight | |

113 | Passive attention in artificial neural networks predicts human visual selectivity | 7.33 | 1.25 | 9, 7, 6 | Oral | Oral | |

114 | Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification | 7.33 | 0.47 | 8, 7, 7 | Oral | Poster | ✔ |

115 | High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails | 7.33 | 0.47 | 7, 8, 7 | Oral | Oral | |

116 | Graphical Models in Heavy-Tailed Markets | 7.33 | 0.47 | 8, 7, 7 | Poster | Poster | |

117 | On Path Integration of Grid Cells: Group Representation and Isotropic Scaling | 7.33 | 2.05 | 10, 5, 7 | Poster | Poster | |

118 | Fast Pure Exploration via Frank-Wolfe | 7.33 | 0.47 | 7, 8, 7 | Poster | Poster | ✔ |

119 | Catch-A-Waveform: Learning to Generate Audio from a Single Short Example | 7.33 | 1.70 | 8, 9, 5 | Poster | Poster | |

120 | Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot? | 7.33 | 0.47 | 7, 7, 8 | Poster | Poster | |

121 | Manifold Topology Divergence: a Framework for Comparing Data Manifolds. | 7.33 | 1.25 | 7, 9, 6 | Poster | Poster | |

122 | Improving Compositionality of Neural Networks by Decoding Representations to Inputs | 7.33 | 0.47 | 7, 8, 7 | Poster | Reject | ✔ |

123 | EditGAN: High-Precision Semantic Image Editing | 7.33 | 0.94 | 8, 6, 8 | Poster | Poster | ✔ |

124 | On the Role of Optimization in Double Descent: A Least Squares Study | 7.33 | 0.47 | 7, 7, 8 | Poster | Poster | ✔ |

125 | ATISS: Autoregressive Transformers for Indoor Scene Synthesis | 7.33 | 0.47 | 8, 7, 7 | Poster | Poster | |

126 | L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization | 7.33 | 0.47 | 7, 8, 7 | Poster | Poster | |

127 | Safe Policy Optimization with Local Generalized Linear Function Approximations | 7.33 | 0.94 | 6, 8, 8 | Poster | Poster | |

128 | Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning | 7.33 | 0.47 | 8, 7, 7 | Poster | Poster | |

129 | Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators | 7.33 | 0.47 | 7, 8, 7 | Poster | Poster | |

130 | Instance-Dependent Partial Label Learning | 7.33 | 0.47 | 7, 7, 8 | Spotlight | Spotlight | |

131 | Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space | 7.33 | 0.47 | 7, 7, 8 | Spotlight | Spotlight | |

132 | PLUGIn: A simple algorithm for inverting generative models with recovery guarantees | 7.33 | 0.47 | 7, 7, 8 | Spotlight | Spotlight | |

133 | PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition | 7.33 | 0.47 | 7, 7, 8 | Spotlight | Spotlight | |

134 | On the Value of Infinite Gradients in Variational Autoencoder Models | 7.33 | 0.47 | 8, 7, 7 | Spotlight | Spotlight | ✔ |

135 | FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout | 7.33 | 0.47 | 7, 7, 8 | Spotlight | Spotlight | |

136 | Near-Optimal Lower Bounds For Convex Optimization For All Orders of Smoothness | 7.33 | 1.25 | 7, 9, 6 | Spotlight | Spotlight | |

137 | Private Non-smooth ERM and SCO in Subquadratic Steps | 7.33 | 0.47 | 8, 7, 7 | Spotlight | Spotlight | |

138 | Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits | 7.33 | 0.47 | 8, 7, 7 | Spotlight | Spotlight | |

139 | Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning | 7.33 | 0.47 | 8, 7, 7 | Spotlight | Spotlight | |

140 | Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay | 7.33 | 0.47 | 8, 7, 7 | Spotlight | Spotlight | |

141 | Learning Debiased Representation via Disentangled Feature Augmentation | 7.25 | 0.43 | 7, 7, 8, 7 | Oral | Oral | |

142 | Risk Monotonicity in Statistical Learning | 7.25 | 1.09 | 6, 7, 7, 9 | Oral | Oral | |

143 | Optimal Rates for Random Order Online Optimization | 7.25 | 0.83 | 7, 8, 8, 6 | Oral | Oral | |

144 | A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference | 7.25 | 0.43 | 7, 7, 7, 8 | Oral | Oral | |

145 | Faster Matchings via Learned Duals | 7.25 | 0.43 | 7, 8, 7, 7 | Oral | Oral | |

146 | Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination | 7.25 | 0.43 | 7, 8, 7, 7 | Oral | Oral | |

147 | The decomposition of the higher-order homology embedding constructed from the
k
-Laplacian | 7.25 | 1.09 | 6, 7, 7, 9 | Oral | Oral | |

148 | Evaluating Gradient Inversion Attacks and Defenses in Federated Learning | 7.25 | 1.09 | 9, 6, 7, 7 | Oral | Oral | |

149 | Framing RNN as a kernel method: A neural ODE approach | 7.25 | 0.43 | 8, 7, 7, 7 | Oral | Oral | |

150 | MERLOT: Multimodal Neural Script Knowledge Models | 7.25 | 0.43 | 7, 7, 8, 7 | Oral | Oral | |

151 | The Complexity of Bayesian Network Learning: Revisiting the Superstructure | 7.25 | 0.43 | 8, 7, 7, 7 | Oral | Oral | |

152 | Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis | 7.25 | 0.43 | 8, 7, 7, 7 | Poster | Poster | |

153 | Concentration inequalities under sub-Gaussian and sub-exponential conditions | 7.25 | 1.09 | 7, 9, 7, 6 | Poster | Poster | |

154 | Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels | 7.25 | 1.48 | 9, 5, 7, 8 | Poster | Poster | |

155 | Information is Power: Intrinsic Control via Information Capture | 7.25 | 0.43 | 8, 7, 7, 7 | Poster | Poster | |

156 | Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP | 7.25 | 0.83 | 7, 8, 8, 6 | Poster | Poster | ✔ |

157 | Learning to Synthesize Programs as Interpretable and Generalizable Policies | 7.25 | 0.43 | 7, 8, 7, 7 | Poster | Poster | |

158 | Scatterbrain: Unifying Sparse and Low-rank Attention | 7.25 | 1.48 | 9, 5, 7, 8 | Poster | Poster | |

159 | Scaling Vision with Sparse Mixture of Experts | 7.25 | 1.09 | 7, 9, 7, 6 | Poster | Poster | ✔ |

160 | Score-based Generative Modeling in Latent Space | 7.25 | 0.83 | 7, 6, 8, 8 | Poster | Poster | |

161 | Powerpropagation: A sparsity inducing weight reparameterisation | 7.25 | 0.43 | 7, 7, 7, 8 | Poster | Poster | |

162 | Three-dimensional spike localization and improved motion correction for Neuropixels recordings | 7.25 | 1.92 | 6, 10, 8, 5 | Poster | Poster | |

163 | Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception | 7.25 | 0.43 | 7, 7, 7, 8 | Poster | Poster | |

164 | Consistent Estimation for PCA and Sparse Regression with Oblivious Outliers | 7.25 | 0.43 | 7, 8, 7, 7 | Poster | Poster | |

165 | Estimating the Unique Information of Continuous Variables | 7.25 | 0.43 | 7, 7, 8, 7 | Poster | Poster | |

166 | Test-time Collective Prediction | 7.25 | 0.43 | 7, 7, 8, 7 | Poster | Poster | |

167 | Continual Auxiliary Task Learning | 7.25 | 0.43 | 7, 7, 8, 7 | Poster | Poster | |

168 | Novel Upper Bounds for the Constrained Most Probable Explanation Task | 7.25 | 0.43 | 7, 7, 7, 8 | Poster | Poster | |

169 | On the Cryptographic Hardness of Learning Single Periodic Neurons | 7.25 | 0.43 | 7, 7, 8, 7 | Poster | Poster | |

170 | On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs) | 7.25 | 0.83 | 8, 7, 8, 6 | Poster | Poster | |

171 | Cardinality constrained submodular maximization for random streams | 7.25 | 0.43 | 7, 7, 8, 7 | Poster | Poster | |

172 | Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA | 7.25 | 0.43 | 8, 7, 7, 7 | Poster | Poster | |

173 | Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge | 7.25 | 0.43 | 8, 7, 7, 7 | Poster | Spotlight | ✔ |

174 | MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images | 7.25 | 0.83 | 7, 8, 8, 6 | Poster | Poster | |

175 | Learning Hard Optimization Problems: A Data Generation Perspective | 7.25 | 0.43 | 7, 7, 7, 8 | Poster | Poster | |

176 | General Nonlinearities in SO(2)-Equivariant CNNs | 7.25 | 0.83 | 8, 7, 6, 8 | Poster | Poster | |

177 | Finding Regions of Heterogeneity in Decision-Making via Expected Conditional Covariance | 7.25 | 1.09 | 9, 7, 6, 7 | Poster | Poster | |

178 | Automated Dynamic Mechanism Design | 7.25 | 0.43 | 7, 7, 7, 8 | Poster | Poster | |

179 | An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks | 7.25 | 0.43 | 7, 7, 7, 8 | Poster | Poster | |

180 | A generative nonparametric Bayesian model for whole genomes | 7.25 | 1.09 | 7, 7, 6, 9 | Poster | Poster | |

181 | ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias | 7.25 | 0.83 | 6, 8, 7, 8 | Poster | Poster | ✔ |

182 | TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning | 7.25 | 1.30 | 6, 9, 8, 6 | Poster | Poster | |

183 | On the Universality of Graph Neural Networks on Large Random Graphs | 7.25 | 1.48 | 9, 7, 8, 5 | Poster | Poster | |

184 | Estimating High Order Gradients of the Data Distribution by Denoising | 7.25 | 0.43 | 7, 7, 8, 7 | Poster | Poster | |

185 | Tensor decompositions of higher-order correlations by nonlinear Hebbian plasticity | 7.25 | 1.09 | 9, 7, 7, 6 | Poster | Poster | |

186 | Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data | 7.25 | 0.43 | 7, 8, 7, 7 | Poster | Poster | |

187 | Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates | 7.25 | 1.09 | 6, 7, 7, 9 | Poster | Poster | |

188 | Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model | 7.25 | 0.43 | 7, 8, 7, 7 | Poster | Poster | |

189 | Structure-Aware Random Fourier Kernel for Graphs | 7.25 | 1.09 | 9, 6, 7, 7 | Poster | Poster | |

190 | Understanding Partial Multi-Label Learning via Mutual Information | 7.25 | 0.83 | 7, 8, 6, 8 | Poster | Poster | |

191 | Universal Semi-Supervised Learning | 7.25 | 1.09 | 7, 7, 9, 6 | Poster | Poster | |

192 | CrypTen: Secure Multi-Party Computation Meets Machine Learning | 7.25 | 0.83 | 8, 6, 8, 7 | Poster | Poster | |

193 | Iterative Teaching by Label Synthesis | 7.25 | 0.83 | 6, 8, 8, 7 | Spotlight | Spotlight | |

194 | Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks | 7.25 | 0.83 | 8, 8, 6, 7 | Spotlight | Spotlight | |

195 | Interactive Label Cleaning with Example-based Explanations | 7.25 | 0.83 | 6, 8, 8, 7 | Spotlight | Spotlight | |

196 | Mixture Proportion Estimation and PU Learning:A Modern Approach | 7.25 | 0.83 | 7, 8, 8, 6 | Spotlight | Spotlight | |

197 | A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition | 7.25 | 1.09 | 9, 7, 7, 6 | Spotlight | Spotlight | |

198 | Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis | 7.25 | 0.43 | 7, 7, 8, 7 | Spotlight | Spotlight | |

199 | RL for Latent MDPs: Regret Guarantees and a Lower Bound | 7.25 | 0.83 | 8, 6, 7, 8 | Spotlight | Spotlight | |

200 | A single gradient step finds adversarial examples on random two-layers neural networks | 7.25 | 0.43 | 8, 7, 7, 7 | Spotlight | Spotlight | |

201 | Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations | 7.25 | 0.43 | 7, 7, 8, 7 | Spotlight | Spotlight | |

202 | The Semi-Random Satisfaction of Voting Axioms | 7.25 | 0.43 | 7, 7, 8, 7 | Spotlight | Spotlight | |

203 | Constrained Robust Submodular Partitioning | 7.25 | 0.43 | 7, 7, 8, 7 | Spotlight | Spotlight | |

204 | Forster Decomposition and Learning Halfspaces with Noise | 7.25 | 0.83 | 8, 8, 6, 7 | Spotlight | Spotlight | ✔ |

205 | Collaborating with Humans without Human Data | 7.25 | 1.48 | 7, 8, 5, 9 | Spotlight | Spotlight | ✔ |

206 | Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning | 7.25 | 0.43 | 8, 7, 7, 7 | Spotlight | Spotlight | |

207 | Mind the Gap: Assessing Temporal Generalization in Neural Language Models | 7.25 | 0.83 | 7, 8, 8, 6 | Spotlight | Spotlight | |

208 | Fair Exploration via Axiomatic Bargaining | 7.25 | 0.43 | 7, 7, 7, 8 | Spotlight | Spotlight | |

209 | Multimodal and Multilingual Embeddings for Large-Scale Speech Mining | 7.25 | 0.43 | 7, 7, 8, 7 | Spotlight | Spotlight | |

210 | Calibration and Consistency of Adversarial Surrogate Losses | 7.25 | 1.30 | 8, 6, 9, 6 | Spotlight | Spotlight | |

211 | The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning | 7.25 | 0.43 | 7, 8, 7, 7 | Spotlight | Spotlight | |

212 | Learning Disentangled Behavior Embeddings | 7.25 | 0.43 | 7, 7, 7, 8 | Spotlight | Spotlight | ✔ |

213 | Shaping embodied agent behavior with activity-context priors from egocentric video | 7.25 | 0.83 | 8, 8, 6, 7 | Spotlight | Spotlight | |

214 | Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms | 7.25 | 0.43 | 7, 8, 7, 7 | Spotlight | Spotlight | |

215 | Efficiently Identifying Task Groupings for Multi-Task Learning | 7.25 | 0.83 | 8, 8, 7, 6 | Spotlight | Spotlight | |

216 | Beyond Tikhonov: faster learning with self-concordant losses, via iterative regularization | 7.25 | 0.43 | 8, 7, 7, 7 | Spotlight | Poster | ✔ |

217 | Online and Offline Reinforcement Learning by Planning with a Learned Model | 7.25 | 0.83 | 8, 6, 7, 8 | Spotlight | Spotlight | |

218 | A
2
-Net: Learning Attribute-Aware Hash Codes for Large-Scale Fine-Grained Image Retrieval | 7.25 | 1.09 | 9, 7, 6, 7 | Spotlight | Spotlight | |

219 | Variational Inference for Continuous-Time Switching Dynamical Systems | 7.25 | 0.43 | 7, 7, 7, 8 | Spotlight | Spotlight | ✔ |

220 | Maximum Likelihood Training of Score-Based Diffusion Models | 7.25 | 0.43 | 7, 7, 8, 7 | Spotlight | Spotlight | |

221 | A Variational Perspective on Diffusion-Based Generative Models and Score Matching | 7.25 | 0.43 | 7, 8, 7, 7 | Spotlight | Spotlight | |

222 | Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation | 7.25 | 0.83 | 6, 8, 7, 8 | Spotlight | Spotlight | |

223 | Pragmatic Image Compression for Human-in-the-Loop Decision-Making | 7.25 | 0.83 | 8, 8, 6, 7 | Spotlight | Spotlight | |

224 | Differential Privacy Over Riemannian Manifolds | 7.20 | 1.60 | 5, 9, 6, 7, 9 | Poster | Poster | |

225 | Unadversarial Examples: Designing Objects for Robust Vision | 7.20 | 0.98 | 7, 6, 9, 7, 7 | Poster | Poster | |

226 | User-Level Differentially Private Learning via Correlated Sampling | 7.20 | 0.40 | 7, 7, 7, 7, 8 | Poster | Poster | ✔ |

227 | PCA Initialization for Approximate Message Passing in Rotationally Invariant Models | 7.20 | 1.60 | 6, 6, 8, 6, 10 | Poster | Poster | |

228 | Multiwavelet-based Operator Learning for Differential Equations | 7.20 | 0.75 | 8, 7, 6, 7, 8 | Spotlight | Spotlight | |

229 | Learning Frequency Domain Approximation for Binary Neural Networks | 7.00 | 0.82 | 6, 7, 8 | Oral | Poster | ✔ |

230 | Sequential Causal Imitation Learning with Unobserved Confounders | 7.00 | 0.71 | 8, 7, 7, 6 | Oral | Poster | ✔ |

231 | Adaptive Conformal Inference Under Distribution Shift | 7.00 | 1.15 | 7, 5, 8, 6, 8, 8 | Oral | Oral | |

232 | Causal Identification with Matrix Equations | 7.00 | 0.82 | 7, 6, 8 | Oral | Oral | ✔ |

233 | Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity | 7.00 | 0.00 | 7, 7, 7 | Oral | Oral | |

234 | E(n) Equivariant Normalizing Flows | 7.00 | 0.00 | 7, 7, 7 | Oral | Oral | |

235 | Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers | 7.00 | 0.00 | 7, 7, 7, 7 | Oral | Oral | |

236 | Towards Efficient and Effective Adversarial Training | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

237 | Neural Routing by Memory | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | ✔ |

238 | Skipping the Frame-Level: Event-Based Piano Transcription With Neural Semi-CRFs | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | ✔ |

239 | Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning | 7.00 | 1.22 | 6, 7, 9, 6 | Poster | Poster | |

240 | Class-agnostic Reconstruction of Dynamic Objects from Videos | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | ✔ |

241 | The Inductive Bias of Quantum Kernels | 7.00 | 0.71 | 7, 7, 6, 8 | Poster | Poster | |

242 | Permuton-induced Chinese Restaurant Process | 7.00 | 0.63 | 8, 7, 7, 6, 7 | Poster | Poster | |

243 | Exponential Graph is Provably Efficient for Decentralized Deep Training | 7.00 | 0.82 | 7, 8, 6 | Poster | Poster | |

244 | Outcome-Driven Reinforcement Learning via Variational Inference | 7.00 | 0.71 | 7, 7, 6, 8 | Poster | Poster | |

245 | Channel Permutations for N:M Sparsity | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

246 | Revisiting Deep Learning Models for Tabular Data | 7.00 | 0.00 | 7, 7, 7, 7, 7 | Poster | Poster | |

247 | Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning | 7.00 | 1.63 | 7, 5, 9 | Poster | Poster | ✔ |

248 | Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning | 7.00 | 0.71 | 8, 7, 7, 6 | Poster | Poster | ✔ |

249 | Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

250 | BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation | 7.00 | 0.82 | 8, 6, 7 | Poster | Poster | |

251 | Overinterpretation reveals image classification model pathologies | 7.00 | 0.71 | 7, 6, 7, 8 | Poster | Poster | |

252 | On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

253 | Implicit Regularization in Matrix Sensing via Mirror Descent | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

254 | Efficient Equivariant Network | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

255 | On Density Estimation with Diffusion Models | 7.00 | 1.22 | 9, 7, 6, 6 | Poster | Poster | |

256 | Revisiting the Calibration of Modern Neural Networks | 7.00 | 0.82 | 7, 6, 8 | Poster | Poster | |

257 | Partition and Code: learning how to compress graphs | 7.00 | 1.22 | 8, 7, 8, 5 | Poster | Poster | |

258 | Adder Attention for Vision Transformer | 7.00 | 0.71 | 7, 7, 8, 6 | Poster | Poster | |

259 | See More for Scene: Pairwise Consistency Learning for Scene Classification | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

260 | Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning | 7.00 | 1.22 | 7, 6, 9, 6 | Poster | Spotlight | ✔ |

261 | Universal Off-Policy Evaluation | 7.00 | 1.41 | 9, 7, 7, 5 | Poster | Poster | |

262 | Generative Occupancy Fields for 3D Surface-Aware Image Synthesis | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

263 | Celebrating Diversity in Shared Multi-Agent Reinforcement Learning | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | |

264 | Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data | 7.00 | 0.71 | 7, 8, 7, 6 | Poster | Poster | |

265 | Efficient Mirror Descent Ascent Methods for Nonsmooth Minimax Problems | 7.00 | 0.82 | 8, 7, 6 | Poster | Poster | |

266 | Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data | 7.00 | 0.71 | 7, 7, 6, 8 | Poster | Poster | |

267 | Support Recovery of Sparse Signals from a Mixture of Linear Measurements | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | ✔ |

268 | Optimal Best-Arm Identification Methods for Tail-Risk Measures | 7.00 | 0.00 | 7, 7, 7, 7, 7 | Poster | Poster | |

269 | Unlabeled Principal Component Analysis | 7.00 | 0.71 | 8, 7, 7, 6 | Poster | Poster | |

270 | Evaluating Efficient Performance Estimators of Neural Architectures | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

271 | Hard-Attention for Scalable Image Classification | 7.00 | 0.63 | 6, 7, 8, 7, 7 | Poster | Poster | |

272 | Canonical Capsules: Self-Supervised Capsules in Canonical Pose | 7.00 | 0.63 | 7, 7, 8, 6, 7 | Poster | Poster | |

273 | Bridging the Imitation Gap by Adaptive Insubordination | 7.00 | 0.82 | 7, 8, 6 | Poster | Poster | |

274 | Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

275 | InfoGCL: Information-Aware Graph Contrastive Learning | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

276 | On the Stochastic Stability of Deep Markov Models | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

277 | On the Value of Interaction and Function Approximation in Imitation Learning | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

278 | Implicit SVD for Graph Representation Learning | 7.00 | 1.41 | 9, 6, 6 | Poster | Poster | |

279 | Learning Optimal Predictive Checklists | 7.00 | 1.22 | 6, 7, 6, 9 | Poster | Poster | |

280 | Realistic evaluation of transductive few-shot learning | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

281 | Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

282 | Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data | 7.00 | 0.71 | 6, 7, 7, 8 | Poster | Poster | |

283 | Parameter Prediction for Unseen Deep Architectures | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

284 | Independent mechanism analysis, a new concept? | 7.00 | 0.63 | 7, 7, 6, 8, 7 | Poster | Poster | |

285 | Subquadratic Overparameterization for Shallow Neural Networks | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

286 | Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets | 7.00 | 0.82 | 8, 6, 7 | Poster | Poster | |

287 | Subgoal Search For Complex Reasoning Tasks | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

288 | Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices | 7.00 | 0.71 | 8, 7, 7, 6 | Poster | Poster | |

289 | Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

290 | Geometry Processing with Neural Fields | 7.00 | 1.22 | 7, 6, 6, 9 | Poster | Poster | |

291 | Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image | 7.00 | 1.00 | 6, 8, 6, 8 | Poster | Poster | |

292 | You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection | 7.00 | 0.82 | 7, 8, 6 | Poster | Poster | |

293 | Exponential Separation between Two Learning Models and Adversarial Robustness | 7.00 | 1.41 | 6, 9, 6 | Poster | Poster | ✔ |

294 | On the Sample Complexity of Learning under Geometric Stability | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | |

295 | Optimality of Zeroth Order Gradient Ascent for Nonlinear Bandit Optimization | 7.00 | 1.22 | 8, 7, 5, 8 | Poster | Poster | |

296 | Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

297 | Group Equivariant Subsampling | 7.00 | 0.71 | 7, 6, 7, 8 | Poster | Poster | |

298 | Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

299 | Contextual Recommendations and Low-Regret Cutting-Plane Algorithms | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

300 | Structured Reordering for Modeling Latent Alignments in Sequence Transduction | 7.00 | 0.71 | 7, 8, 6, 7 | Poster | Poster | |

301 | Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

302 | Probabilistic Transformer For Time Series Analysis | 7.00 | 1.58 | 6, 9, 5, 8 | Poster | Poster | |

303 | Play to Grade: Testing Coding Games as Classifying Markov Decision Process | 7.00 | 1.41 | 9, 6, 6 | Poster | Poster | ✔ |

304 | Play to Grade: Testing Coding Games as Classifying Markov Decision Process | 7.00 | 0.82 | 8, 6, 7 | Poster | Poster | ✔ |

305 | Improved Guarantees for Offline Stochastic Matching via new Ordered Contention Resolution Schemes | 7.00 | 0.71 | 7, 8, 7, 6 | Poster | Poster | |

306 | Representation Costs of Linear Neural Networks: Analysis and Design | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | ✔ |

307 | Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models | 7.00 | 0.63 | 7, 8, 7, 6, 7 | Poster | Poster | ✔ |

308 | Robust Online Correlation Clustering | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

309 | Gradual Domain Adaptation without Indexed Intermediate Domains | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

310 | Bayesian Optimization with High-Dimensional Outputs | 7.00 | 0.71 | 6, 8, 7, 7 | Poster | Poster | |

311 | Online false discovery rate control for anomaly detection in time series | 7.00 | 1.22 | 9, 6, 7, 6 | Poster | Poster | |

312 | A Topological Perspective on Causal Inference | 7.00 | 0.63 | 7, 7, 7, 6, 8 | Poster | Poster | |

313 | Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning | 7.00 | 1.00 | 8, 6, 6, 8 | Poster | Poster | ✔ |

314 | Fast rates for prediction with limited expert advice | 7.00 | 0.71 | 7, 6, 7, 8 | Poster | Poster | |

315 | Tactical Optimism and Pessimism for Deep Reinforcement Learning | 7.00 | 1.22 | 9, 6, 7, 6 | Poster | Poster | |

316 | Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

317 | A Domain-Shrinking based Bayesian Optimization Algorithm with Order-Optimal Regret Performance | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

318 | Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games | 7.00 | 0.71 | 6, 8, 7, 7 | Poster | Poster | |

319 | Online Learning Of Neural Computations From Sparse Temporal Feedback | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

320 | When Is Generalizable Reinforcement Learning Tractable? | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

321 | Towards understanding retrosynthesis by energy-based models | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

322 | Attention Bottlenecks for Multimodal Fusion | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

323 | Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

324 | Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information | 7.00 | 0.82 | 7, 8, 6 | Poster | Poster | |

325 | Convergence and Alignment of Gradient Descent with Random Backpropagation Weights | 7.00 | 0.63 | 7, 7, 8, 6, 7 | Poster | Poster | |

326 | Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning | 7.00 | 0.71 | 7, 8, 7, 6 | Poster | Poster | |

327 | Roto-translated Local Coordinate Frames For Interacting Dynamical Systems | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

328 | Closing the loop in medical decision support by understanding clinical decision-making: A case study on organ transplantation | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

329 | Causal Influence Detection for Improving Efficiency in Reinforcement Learning | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

330 | Iterative Connecting Probability Estimation for Networks | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

331 | Best-case lower bounds in online learning | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

332 | DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

333 | Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients | 7.00 | 1.22 | 7, 8, 8, 5 | Poster | Poster | |

334 | Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality | 7.00 | 0.71 | 7, 8, 7, 6 | Poster | Poster | |

335 | Landscape analysis of an improved power method for tensor decomposition | 7.00 | 1.22 | 6, 9, 6, 7 | Poster | Poster | |

336 | Cycle Self-Training for Domain Adaptation | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

337 | On Calibration and Out-of-Domain Generalization | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

338 | Sparse Training via Boosting Pruning Plasticity with Neuroregeneration | 7.00 | 0.82 | 6, 8, 7 | Poster | Poster | |

339 | You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership | 7.00 | 0.63 | 7, 6, 7, 8, 7 | Poster | Poster | |

340 | Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time | 7.00 | 0.82 | 6, 8, 7 | Poster | Poster | ✔ |

341 | Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

342 | Identifiable Generative models for Missing Not at Random Data Imputation | 7.00 | 0.71 | 7, 8, 6, 7 | Poster | Poster | |

343 | Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures | 7.00 | 1.22 | 6, 7, 6, 9 | Poster | Poster | |

344 | Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

345 | Black Box Probabilistic Numerics | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

346 | Introspective Distillation for Robust Question Answering | 7.00 | 0.71 | 6, 7, 7, 8 | Poster | Poster | |

347 | There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning | 7.00 | 1.58 | 9, 5, 6, 8 | Poster | Poster | |

348 | Formalizing the Generalization-Forgetting Trade-off in Continual Learning | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

349 | Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs | 7.00 | 0.71 | 6, 8, 7, 7 | Poster | Poster | |

350 | Machine learning structure preserving brackets for forecasting irreversible processes | 7.00 | 0.82 | 8, 6, 7 | Poster | Spotlight | ✔ |

351 | Parameter Inference with Bifurcation Diagrams | 7.00 | 0.82 | 7, 6, 8 | Poster | Poster | |

352 | How Powerful are Performance Predictors in Neural Architecture Search? | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

353 | Gauge Equivariant Transformer | 7.00 | 0.89 | 8, 6, 7, 8, 6 | Poster | Poster | |

354 | Multi-Label Learning with Pairwise Relevance Ordering | 7.00 | 1.00 | 8, 8, 6, 6 | Poster | Poster | |

355 | Multimodal Few-Shot Learning with Frozen Language Models | 7.00 | 0.71 | 8, 7, 7, 6 | Poster | Poster | |

356 | Robust and differentially private mean estimation | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

357 | Multiclass versus Binary Differentially Private PAC Learning | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

358 | K-Net: Towards Unified Image Segmentation | 7.00 | 1.22 | 6, 6, 7, 9 | Poster | Poster | |

359 | On Locality of Local Explanation Models | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

360 | Searching for Efficient Transformers for Language Modeling | 7.00 | 1.41 | 9, 7, 5, 7 | Poster | Poster | |

361 | Statistically and Computationally Efficient Linear Meta-representation Learning | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

362 | From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

363 | Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote | 7.00 | 1.26 | 5, 7, 7, 7, 9 | Poster | Poster | ✔ |

364 | NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform | 7.00 | 1.22 | 6, 9, 6, 7 | Poster | Poster | ✔ |

365 | A Non-commutative Extension of Lee-Seung's Algorithm for Positive Semidefinite Factorizations | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

366 | BARTScore: Evaluating Generated Text as Text Generation | 7.00 | 1.00 | 6, 8, 6, 8 | Poster | Poster | |

367 | Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

368 | Safe Pontryagin Differentiable Programming | 7.00 | 1.22 | 9, 7, 6, 6 | Poster | Poster | |

369 | On the Variance of the Fisher Information for Deep Learning | 7.00 | 0.82 | 7, 8, 6 | Poster | Poster | |

370 | Probabilistic Margins for Instance Reweighting in Adversarial Training | 7.00 | 0.71 | 8, 7, 7, 6 | Poster | Poster | |

371 | An Exact Characterization of the Generalization Error for the Gibbs Algorithm | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

372 | Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium | 7.00 | 1.41 | 8, 5, 8 | Poster | Poster | |

373 | ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

374 | Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects | 7.00 | 1.22 | 6, 9, 6, 7 | Poster | Poster | |

375 | Nonparametric estimation of continuous DPPs with kernel methods | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

376 | Graph Differentiable Architecture Search with Structure Learning | 7.00 | 1.22 | 6, 9, 7, 6 | Poster | Poster | |

377 | Modular Gaussian Processes for Transfer Learning | 7.00 | 1.22 | 6, 6, 9, 7 | Poster | Poster | |

378 | Smooth Bilevel Programming for Sparse Regularization | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | |

379 | Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

380 | Invertible Tabular GANs: Killing Two Birds with One Stone for Tabular Data Synthesis | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

381 | Learning Nonparametric Volterra Kernels with Gaussian Processes | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

382 | On Blame Attribution for Accountable Multi-Agent Sequential Decision Making | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

383 | Efficiently Learning One Hidden Layer ReLU Networks From Queries | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

384 | Does Preprocessing Help Training Over-parameterized Neural Networks? | 7.00 | 0.82 | 8, 6, 7 | Poster | Poster | |

385 | Why Spectral Normalization Stabilizes GANs: Analysis and Improvements | 7.00 | 0.71 | 7, 7, 8, 6 | Poster | Poster | |

386 | Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases | 7.00 | 0.82 | 8, 6, 7 | Poster | Poster | ✔ |

387 | Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

388 | Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss | 7.00 | 0.82 | 7, 6, 8 | Poster | Poster | |

389 | Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods | 7.00 | 0.71 | 7, 8, 7, 6 | Poster | Poster | |

390 | Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

391 | Decision Transformer: Reinforcement Learning via Sequence Modeling | 7.00 | 1.22 | 9, 7, 6, 6 | Poster | Poster | |

392 | SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

393 | The Complexity of Sparse Tensor PCA | 7.00 | 0.63 | 7, 7, 6, 8, 7 | Poster | Poster | |

394 | Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

395 | Detecting Anomalous Event Sequences with Temporal Point Processes | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

396 | The Pareto Frontier of model selection for general Contextual Bandits | 7.00 | 1.22 | 8, 7, 5, 8 | Poster | Poster | |

397 | Machine Learning for Variance Reduction in Online Experiments | 7.00 | 1.41 | 7, 5, 9, 7 | Poster | Poster | |

398 | Provably Strict Generalisation Benefit for Invariance in Kernel Methods | 7.00 | 1.41 | 7, 9, 5, 7 | Poster | Poster | ✔ |

399 | On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

400 | Impression learning: Online representation learning with synaptic plasticity | 7.00 | 0.71 | 7, 7, 6, 8 | Poster | Poster | |

401 | Neural Flows: Efficient Alternative to Neural ODEs | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

402 | Distributed Zero-Order Optimization under Adversarial Noise | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

403 | Hyperbolic Busemann Learning with Ideal Prototypes | 7.00 | 0.82 | 7, 8, 6 | Poster | Poster | |

404 | Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data | 7.00 | 0.82 | 8, 7, 6 | Poster | Poster | |

405 | Shared Independent Component Analysis for Multi-Subject Neuroimaging | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

406 | Partition-Based Formulations for Mixed-Integer Optimization of Trained ReLU Neural Networks | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

407 | Adversarial Regression with Doubly Non-negative Weighting Matrices | 7.00 | 0.63 | 7, 8, 7, 6, 7 | Poster | Poster | ✔ |

408 | Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Poster | |

409 | Deep Residual Learning in Spiking Neural Networks | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

410 | Generalizable Multi-linear Attention Network | 7.00 | 0.82 | 7, 6, 8 | Poster | Poster | |

411 | Local plasticity rules can learn deep representations using self-supervised contrastive predictions | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

412 | Integrated Latent Heterogeneity and Invariance Learning in Kernel Space | 7.00 | 0.71 | 8, 7, 7, 6 | Poster | Poster | |

413 | Conditional Generation Using Polynomial Expansions | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Spotlight | ✔ |

414 | User-Level Differentially Private Learning via Correlated Sampling | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

415 | Nearly-Tight and Oblivious Algorithms for Explainable Clustering | 7.00 | 0.71 | 8, 7, 6, 7 | Poster | Spotlight | ✔ |

416 | Nearly-Tight and Oblivious Algorithms for Explainable Clustering | 7.00 | 0.71 | 7, 6, 7, 8 | Poster | Poster | ✔ |

417 | Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning | 7.00 | 1.00 | 6, 8, 8, 6 | Poster | Poster | |

418 | Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm | 7.00 | 0.71 | 7, 6, 7, 8 | Poster | Poster | |

419 | Demystifying and Generalizing BinaryConnect | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

420 | Contextual Similarity Aggregation with Self-attention for Visual Re-ranking | 7.00 | 0.71 | 7, 6, 7, 8 | Poster | Poster | |

421 | On the Sample Complexity of Privately Learning Axis-Aligned Rectangles | 7.00 | 1.22 | 9, 6, 7, 6 | Poster | Poster | |

422 | Low-Rank Extragradient Method for Nonsmooth and Low-Rank Matrix Optimization Problems | 7.00 | 1.41 | 9, 6, 6 | Poster | Poster | ✔ |

423 | Invertible DenseNets with Concatenated LipSwish | 7.00 | 0.71 | 6, 8, 7, 7 | Poster | Poster | |

424 | NORESQA: A Framework for Speech Quality Assessment using Non-Matching References | 7.00 | 0.82 | 8, 7, 6 | Poster | Poster | |

425 | SBO-RNN: Reformulating Recurrent Neural Networks via Stochastic Bilevel Optimization | 7.00 | 0.71 | 7, 8, 6, 7 | Poster | Poster | ✔ |

426 | Learning in Multi-Stage Decentralized Matching Markets | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | |

427 | Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective | 7.00 | 0.71 | 6, 7, 8, 7 | Poster | Poster | |

428 | Learning Space Partitions for Path Planning | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

429 | Recursive Causal Structure Learning in the Presence of Latent Variables and Selection Bias | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | ✔ |

430 | Iterative Amortized Policy Optimization | 7.00 | 0.71 | 6, 8, 7, 7 | Poster | Poster | |

431 | Predicting Event Memorability from Contextual Visual Semantics | 7.00 | 0.71 | 7, 7, 8, 6 | Poster | Poster | |

432 | MICo: Improved representations via sampling-based state similarity for Markov decision processes | 7.00 | 0.00 | 7, 7, 7, 7 | Poster | Poster | |

433 | On the Suboptimality of Thompson Sampling in High Dimensions | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | |

434 | Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

435 | Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

436 | Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions | 7.00 | 1.00 | 8, 8, 6, 6 | Poster | Poster | |

437 | Beltrami Flow and Neural Diffusion on Graphs | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

438 | Stabilizing Dynamical Systems via Policy Gradient Methods | 7.00 | 0.00 | 7, 7, 7 | Poster | Poster | |

439 | SE(3)-equivariant prediction of molecular wavefunctions and electronic densities | 7.00 | 0.71 | 7, 6, 8, 7 | Poster | Poster | |

440 | General Low-rank Matrix Optimization: Geometric Analysis and Sharper Bounds | 7.00 | 0.71 | 8, 6, 7, 7 | Poster | Poster | |

441 | Self-Supervised Bug Detection and Repair | 7.00 | 1.63 | 5, 9, 7 | Poster | Poster | ✔ |

442 | Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning | 7.00 | 0.82 | 6, 8, 7 | Poster | Poster | |

443 | Subgroup Generalization and Fairness of Graph Neural Networks | 7.00 | 0.71 | 7, 8, 6, 7 | Spotlight | Spotlight | |

444 | Rethinking gradient sparsification as total error minimization | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

445 | Look at What I’m Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos | 7.00 | 0.71 | 7, 8, 6, 7 | Spotlight | Spotlight | |

446 | Continuous vs. Discrete Optimization of Deep Neural Networks | 7.00 | 0.63 | 8, 7, 7, 6, 7 | Spotlight | Spotlight | ✔ |

447 | SOFT: Softmax-free Transformer with Linear Complexity | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

448 | Fast Bayesian Inference for Gaussian Cox Processes via Path Integral Formulation | 7.00 | 1.41 | 9, 7, 5, 7 | Spotlight | Spotlight | |

449 | DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

450 | Second-Order Neural ODE Optimizer | 7.00 | 0.71 | 7, 6, 7, 8 | Spotlight | Spotlight | |

451 | Lossy Compression for Lossless Prediction | 7.00 | 0.71 | 8, 7, 7, 6 | Spotlight | Spotlight | |

452 | Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima | 7.00 | 1.22 | 9, 7, 6, 6 | Spotlight | Spotlight | |

453 | Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution | 7.00 | 0.71 | 7, 7, 6, 8 | Spotlight | Spotlight | |

454 | Neural optimal feedback control with local learning rules | 7.00 | 0.71 | 7, 7, 8, 6 | Spotlight | Spotlight | |

455 | Counterfactual Invariance to Spurious Correlations in Text Classification | 7.00 | 0.71 | 7, 7, 6, 8 | Spotlight | Spotlight | |

456 | H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion | 7.00 | 0.71 | 6, 7, 7, 8 | Spotlight | Spotlight | |

457 | Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | ✔ |

458 | Learning Large Neighborhood Search Policy for Integer Programming | 7.00 | 0.71 | 7, 8, 6, 7 | Spotlight | Spotlight | |

459 | Optimal Sketching for Trace Estimation | 7.00 | 0.71 | 8, 7, 6, 7 | Spotlight | Spotlight | |

460 | Uniform Sampling over Episode Difficulty | 7.00 | 1.00 | 6, 8, 6, 8 | Spotlight | Spotlight | |

461 | Intriguing Properties of Vision Transformers | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

462 | Learning to delegate for large-scale vehicle routing | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

463 | Behavior From the Void: Unsupervised Active Pre-Training | 7.00 | 0.71 | 6, 7, 7, 8 | Spotlight | Spotlight | |

464 | Long Short-Term Transformer for Online Action Detection | 7.00 | 0.71 | 8, 6, 7, 7 | Spotlight | Spotlight | |

465 | Flexible Option Learning | 7.00 | 0.82 | 8, 6, 7 | Spotlight | Spotlight | |

466 | Efficient Online Estimation of Causal Effects by Deciding What to Observe | 7.00 | 0.71 | 7, 6, 7, 8 | Spotlight | Spotlight | |

467 | Auditing Black-Box Prediction Models for Data Minimization Compliance | 7.00 | 0.82 | 8, 6, 7 | Spotlight | Spotlight | |

468 | Robust Learning of Optimal Auctions | 7.00 | 0.82 | 6, 8, 7 | Spotlight | Spotlight | |

469 | Double Machine Learning Density Estimation for Local Treatment Effects with Instruments | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

470 | GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles | 7.00 | 0.00 | 7, 7, 7 | Spotlight | Spotlight | |

471 | Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

472 | Speedy Performance Estimation for Neural Architecture Search | 7.00 | 0.71 | 6, 8, 7, 7 | Spotlight | Spotlight | |

473 | A Central Limit Theorem for Differentially Private Query Answering | 7.00 | 0.71 | 7, 8, 7, 6 | Spotlight | Spotlight | |

474 | Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

475 | PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair | 7.00 | 0.71 | 7, 7, 8, 6 | Spotlight | Spotlight | |

476 | Reinforcement Learning in Newcomblike Environments | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

477 | Robust Predictable Control | 7.00 | 0.71 | 7, 7, 6, 8 | Spotlight | Spotlight | |

478 | Online Selective Classification with Limited Feedback | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

479 | Proper Value Equivalence | 7.00 | 0.71 | 8, 7, 7, 6 | Spotlight | Spotlight | |

480 | Task-Adaptive Neural Network Retrieval with Meta-Contrastive Learning | 7.00 | 0.71 | 8, 7, 7, 6 | Spotlight | Spotlight | |

481 | Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

482 | Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation | 7.00 | 0.00 | 7, 7, 7 | Spotlight | Spotlight | |

483 | Learning with Holographic Reduced Representations | 7.00 | 0.71 | 7, 6, 7, 8 | Spotlight | Spotlight | ✔ |

484 | Repulsive Deep Ensembles are Bayesian | 7.00 | 0.71 | 6, 7, 7, 8 | Spotlight | Spotlight | |

485 | Dense Keypoints via Multiview Supervision | 7.00 | 0.58 | 7, 8, 7, 6, 7, 7 | Spotlight | Spotlight | |

486 | Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems | 7.00 | 0.71 | 8, 7, 7, 6 | Spotlight | Spotlight | |

487 | Early-stopped neural networks are consistent | 7.00 | 0.89 | 6, 8, 8, 6, 7 | Spotlight | Spotlight | ✔ |

488 | A Provably Efficient Sample Collection Strategy for Reinforcement Learning | 7.00 | 0.71 | 6, 7, 7, 8 | Spotlight | Spotlight | |

489 | Uniform Concentration Bounds toward a Unified Framework for Robust Clustering | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

490 | On the Power of Differentiable Learning versus PAC and SQ Learning | 7.00 | 0.00 | 7, 7, 7 | Spotlight | Spotlight | ✔ |

491 | On the Power of Differentiable Learning versus PAC and SQ Learning | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Poster | ✔ |

492 | Bootstrap Your Object Detector via Mixed Training | 7.00 | 0.71 | 6, 7, 7, 8 | Spotlight | Spotlight | |

493 | Precise characterization of the prior predictive distribution of deep ReLU networks | 7.00 | 0.82 | 8, 7, 6 | Spotlight | Spotlight | |

494 | A flow-based latent state generative model of neural population responses to natural images | 7.00 | 0.71 | 7, 8, 6, 7 | Spotlight | Spotlight | |

495 | Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update | 7.00 | 0.71 | 7, 8, 6, 7 | Spotlight | Spotlight | |

496 | ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction | 7.00 | 0.71 | 7, 7, 8, 6 | Spotlight | Spotlight | |

497 | Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

498 | Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems | 7.00 | 1.00 | 6, 8, 6, 8 | Spotlight | Spotlight | |

499 | SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search | 7.00 | 1.00 | 6, 6, 8, 8 | Spotlight | Spotlight | |

500 | Subgame solving without common knowledge | 7.00 | 0.71 | 7, 6, 7, 8 | Spotlight | Spotlight | |

501 | An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | ✔ |

502 | Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning | 7.00 | 0.00 | 7, 7, 7 | Spotlight | Spotlight | |

503 | Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark | 7.00 | 0.82 | 7, 8, 6 | Spotlight | Spotlight | |

504 | On the Existence of The Adversarial Bayes Classifier | 7.00 | 0.82 | 6, 8, 7 | Spotlight | Spotlight | |

505 | Safe Reinforcement Learning with Natural Language Constraints | 7.00 | 0.82 | 6, 7, 8 | Spotlight | Spotlight | |

506 | Tractable Regularization of Probabilistic Circuits | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

507 | Necessary and sufficient graphical conditions for optimal adjustment sets in causal graphical models with hidden variables | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

508 | Batch Normalization Orthogonalizes Representations in Deep Random Networks | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

509 | SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression | 7.00 | 1.41 | 9, 6, 6 | Spotlight | Spotlight | |

510 | Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions | 7.00 | 0.82 | 6, 7, 8 | Spotlight | Spotlight | |

511 | Excess Capacity and Backdoor Poisoning | 7.00 | 0.71 | 6, 8, 7, 7 | Spotlight | Spotlight | |

512 | Your head is there to move you around: Goal-driven models of the primate dorsal pathway | 7.00 | 0.71 | 7, 6, 7, 8 | Spotlight | Spotlight | |

513 | Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

514 | How Well do Feature Visualizations Support Causal Understanding of CNN Activations? | 7.00 | 0.82 | 7, 6, 8 | Spotlight | Spotlight | |

515 | Per-Pixel Classification is Not All You Need for Semantic Segmentation | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

516 | Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space | 7.00 | 0.00 | 7, 7, 7 | Spotlight | Spotlight | |

517 | Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

518 | Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices | 7.00 | 0.71 | 8, 6, 7, 7 | Spotlight | Spotlight | |

519 | Logarithmic Regret in Feature-based Dynamic Pricing | 7.00 | 1.22 | 7, 6, 6, 9 | Spotlight | Spotlight | |

520 | Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State | 7.00 | 0.71 | 7, 8, 7, 6 | Spotlight | Spotlight | |

521 | Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets | 7.00 | 0.82 | 8, 7, 6 | Spotlight | Spotlight | |

522 | Sliced Mutual Information: A Scalable Measure of Statistical Dependence | 7.00 | 0.71 | 8, 7, 7, 6 | Spotlight | Spotlight | ✔ |

523 | On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method | 7.00 | 0.71 | 7, 7, 6, 8 | Spotlight | Spotlight | |

524 | Refined Learning Bounds for Kernel and Approximate
k
-Means | 7.00 | 0.71 | 7, 7, 6, 8 | Spotlight | Spotlight | |

525 | Neural Algorithmic Reasoners are Implicit Planners | 7.00 | 0.71 | 6, 7, 8, 7 | Spotlight | Spotlight | |

526 | Information Directed Sampling for Sparse Linear Bandits | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

527 | Representation Learning Beyond Linear Prediction Functions | 7.00 | 0.00 | 7, 7, 7, 7 | Spotlight | Spotlight | |

528 | Universal Approximation Using Well-Conditioned Normalizing Flows | 6.86 | 0.35 | 7, 7, 6, 7, 7, 7, 7 | Poster | Poster | ✔ |

529 | Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding | 6.83 | 1.34 | 8, 7, 9, 6, 5, 6 | Poster | Poster | ✔ |

530 | Overparameterization Improves Robustness to Covariate Shift in High Dimensions | 6.80 | 0.75 | 6, 8, 6, 7, 7 | Poster | Poster | |

531 | ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees | 6.80 | 1.17 | 8, 5, 7, 8, 6 | Poster | Poster | |

532 | Why Do Better Loss Functions Lead to Less Transferable Features? | 6.80 | 1.33 | 6, 5, 9, 7, 7 | Poster | Poster | |

533 | Augmented Shortcuts for Vision Transformers | 6.80 | 0.75 | 6, 6, 7, 7, 8 | Poster | Poster | |

534 | The Causal-Neural Connection: Expressiveness, Learnability, and Inference | 6.80 | 0.75 | 6, 7, 8, 7, 6 | Poster | Poster | |

535 | Stronger NAS with Weaker Predictors | 6.80 | 0.75 | 6, 7, 6, 7, 8 | Poster | Poster | ✔ |

536 | Bandit Learning with Delayed Impact of Actions | 6.80 | 0.40 | 7, 7, 7, 6, 7 | Poster | Spotlight | ✔ |

537 | Distribution-free inference for regression: discrete, continuous, and in between | 6.80 | 0.98 | 7, 7, 7, 5, 8 | Poster | Poster | ✔ |

538 | Global Filter Networks for Image Classification | 6.80 | 0.40 | 7, 7, 7, 7, 6 | Poster | Poster | |

539 | A nonparametric method for gradual change problems with statistical guarantees | 6.80 | 0.98 | 7, 7, 7, 5, 8 | Poster | Spotlight | ✔ |

540 | Scalable Inference of Sparsely-changing Gaussian Markov Random Fields | 6.80 | 0.75 | 6, 7, 8, 6, 7 | Poster | Poster | |

541 | Learning to Compose Visual Relations | 6.80 | 0.75 | 8, 7, 6, 6, 7 | Spotlight | Spotlight | |

542 | Adversarial Teacher-Student Representation Learning for Domain Generalization | 6.80 | 0.40 | 7, 7, 6, 7, 7 | Spotlight | Spotlight | |

543 | Bayesian decision-making under misspecified priors with applications to meta-learning | 6.80 | 0.98 | 7, 8, 7, 7, 5 | Spotlight | Spotlight | |

544 | Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics | 6.75 | 1.79 | 5, 5, 9, 8 | Oral | Oral | |

545 | TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

546 | Active Learning of Convex Halfspaces on Graphs | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | ✔ |

547 | Visual Adversarial Imitation Learning using Variational Models | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | |

548 | Stochastic Multi-Armed Bandits with Control Variates | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

549 | Network-to-Network Regularization: Enforcing Occam's Razor to Improve Generalization | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

550 | An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

551 | When Expressivity Meets Trainability: Fewer than
n
Neurons Can Work | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | ✔ |

552 | Analytic Insights into Structure and Rank of Neural Network Hessian Maps | 6.75 | 1.30 | 8, 6, 8, 5 | Poster | Poster | |

553 | M-FAC: Efficient Matrix-Free Approximations of Second-Order Information | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

554 | No-regret Online Learning over Riemannian Manifolds | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

555 | A Law of Iterated Logarithm for Multi-Agent Reinforcement Learning | 6.75 | 0.83 | 6, 6, 8, 7 | Poster | Poster | |

556 | Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

557 | FLEX: Unifying Evaluation for Few-Shot NLP | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

558 | Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex | 6.75 | 0.83 | 7, 6, 6, 8 | Poster | Poster | |

559 | Characterizing possible failure modes in physics-informed neural networks | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

560 | Label consistency in overfitted generalized
k
-means | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

561 | Spatio-Temporal Variational Gaussian Processes | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

562 | Modified Frank Wolfe in Probability Space | 6.75 | 1.79 | 8, 9, 5, 5 | Poster | Poster | |

563 | Leveraging Distribution Alignment via Stein Path for Cross-Domain Cold-Start Recommendation | 6.75 | 1.48 | 9, 5, 7, 6 | Poster | Poster | |

564 | Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

565 | RMIX: Learning Risk-Sensitive Policies forCooperative Reinforcement Learning Agents | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

566 | SOPE: Spectrum of Off-Policy Estimators | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

567 | Reliable Causal Discovery with Improved Exact Search and Weaker Assumptions | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

568 | Best of Both Worlds: Practical and Theoretically Optimal Submodular Maximization in Parallel | 6.75 | 0.83 | 7, 8, 6, 6 | Poster | Poster | |

569 | Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP | 6.75 | 1.09 | 7, 8, 5, 7 | Poster | Poster | ✔ |

570 | Identification of Partially Observed Linear Causal Models: Graphical Conditions for the Non-Gaussian and Heterogeneous Cases | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

571 | Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | ✔ |

572 | Asymptotics of representation learning in finite Bayesian neural networks | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

573 | Convex-Concave Min-Max Stackelberg Games | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

574 | Control Variates for Slate Off-Policy Evaluation | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

575 | Unique sparse decomposition of low rank matrices | 6.75 | 1.48 | 6, 5, 7, 9 | Poster | Poster | |

576 | Transformer in Transformer | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

577 | Selective Sampling for Online Best-arm Identification | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

578 | Policy Learning Using Weak Supervision | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

579 | Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

580 | Neural Auto-Curricula in Two-Player Zero-Sum Games | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

581 | Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems | 6.75 | 0.83 | 7, 6, 6, 8 | Poster | Poster | ✔ |

582 | Do Transformers Really Perform Badly for Graph Representation? | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

583 | BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

584 | Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

585 | MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanisms | 6.75 | 1.48 | 5, 7, 9, 6 | Poster | Poster | |

586 | VoiceMixer: Adversarial Voice Style Mixup | 6.75 | 1.64 | 8, 8, 7, 4 | Poster | Poster | ✔ |

587 | Understanding the Effect of Stochasticity in Policy Optimization | 6.75 | 0.83 | 7, 6, 8, 6 | Poster | Poster | |

588 | On Training Implicit Models | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

589 | Analysis of one-hidden-layer neural networks via the resolvent method | 6.75 | 0.83 | 8, 6, 6, 7 | Poster | Poster | |

590 | Dissecting the Diffusion Process in Linear Graph Convolutional Networks | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

591 | Scaling Vision with Sparse Mixture of Experts | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | ✔ |

592 | Perceptual Score: What Data Modalities Does Your Model Perceive? | 6.75 | 0.83 | 8, 7, 6, 6 | Poster | Poster | |

593 | Conservative Data Sharing for Multi-Task Offline Reinforcement Learning | 6.75 | 0.83 | 7, 8, 6, 6 | Poster | Poster | |

594 | Generalized Shape Metrics on Neural Representations | 6.75 | 1.30 | 6, 6, 9, 6 | Poster | Poster | |

595 | You Are the Best Reviewer of Your Own Papers: An Owner-Assisted Scoring Mechanism | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

596 | On the Frequency Bias of Generative Models | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

597 | Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions | 6.75 | 1.30 | 5, 6, 8, 8 | Poster | Poster | |

598 | Escape saddle points by a simple gradient-descent based algorithm | 6.75 | 0.83 | 7, 6, 8, 6 | Poster | Poster | |

599 | XCiT: Cross-Covariance Image Transformers | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

600 | Can contrastive learning avoid shortcut solutions? | 6.75 | 0.83 | 6, 8, 7, 6 | Poster | Poster | |

601 | Reliable Decisions with Threshold Calibration | 6.75 | 1.79 | 9, 4, 7, 7 | Poster | Poster | ✔ |

602 | Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

603 | Uncertainty Calibration for Ensemble-Based Debiasing Methods | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

604 | Learning with User-Level Privacy | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

605 | Generalizable Imitation Learning from Observation via Inferring Goal Proximity | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

606 | Unbiased Classification through Bias-Contrastive and Bias-Balanced Learning | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

607 | MOMA: Multi-Object Multi-Actor Activity Parsing | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

608 | SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition | 6.75 | 0.83 | 8, 6, 6, 7 | Poster | Poster | |

609 | Bandit Phase Retrieval | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

610 | Adversarially robust learning for security-constrained optimal power flow | 6.75 | 0.83 | 6, 7, 6, 8 | Poster | Poster | |

611 | Learning to Select Exogenous Events for Marked Temporal Point Process | 6.75 | 0.83 | 8, 7, 6, 6 | Poster | Poster | |

612 | Algorithmic Instabilities of Accelerated Gradient Descent | 6.75 | 1.48 | 9, 5, 6, 7 | Poster | Poster | |

613 | Fairness via Representation Neutralization | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | ✔ |

614 | Estimating the Long-Term Effects of Novel Treatments | 6.75 | 0.83 | 8, 7, 6, 6 | Poster | Poster | |

615 | Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | |

616 | Blending Anti-Aliasing into Vision Transformer | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

617 | Emergent Communication of Generalizations | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

618 | PSD Representations for Effective Probability Models | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

619 | Online Knapsack with Frequency Predictions | 6.75 | 0.83 | 7, 6, 8, 6 | Poster | Spotlight | ✔ |

620 | Grounding Representation Similarity Through Statistical Testing | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

621 | Boosting with Multiple Sources | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

622 | Locality defeats the curse of dimensionality in convolutional teacher-student scenarios | 6.75 | 1.09 | 5, 8, 7, 7 | Poster | Poster | |

623 | Learning to Schedule Heuristics in Branch and Bound | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | ✔ |

624 | Efficient Training of Retrieval Models using Negative Cache | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

625 | Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

626 | Asynchronous Decentralized SGD with Quantized and Local Updates | 6.75 | 0.83 | 7, 8, 6, 6 | Poster | Poster | |

627 | Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

628 | Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

629 | Dynamic population-based meta-learning for multi-agent communication with natural language | 6.75 | 1.48 | 7, 5, 6, 9 | Poster | Poster | |

630 | Learning in two-player zero-sum partially observable Markov games with perfect recall | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

631 | COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

632 | Meta-Adaptive Nonlinear Control: Theory and Algorithms | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | ✔ |

633 | Fair Sortition Made Transparent | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

634 | Meta Learning Backpropagation And Improving It | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | |

635 | CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

636 | Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

637 | SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization | 6.75 | 1.09 | 5, 7, 8, 7 | Poster | Poster | ✔ |

638 | Revenue maximization via machine learning with noisy data | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

639 | Statistical Undecidability in Linear, Non-Gaussian Causal Models in the Presence of Latent Confounders | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

640 | DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning | 6.75 | 1.30 | 6, 6, 6, 9 | Poster | Poster | |

641 | Marginalised Gaussian Processes with Nested Sampling | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

642 | The staircase property: How hierarchical structure can guide deep learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

643 | Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

644 | How Tight Can PAC-Bayes be in the Small Data Regime? | 6.75 | 0.83 | 7, 8, 6, 6 | Poster | Poster | |

645 | Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | |

646 | On Empirical Risk Minimization with Dependent and Heavy-Tailed Data | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | |

647 | BAST: Bayesian Additive Regression Spanning Trees for Complex Constrained Domain | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

648 | Robust Optimization for Multilingual Translation with Imbalanced Data | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | |

649 | Nearly Horizon-Free Offline Reinforcement Learning | 6.75 | 1.30 | 6, 6, 9, 6 | Poster | Poster | |

650 | Conservative Offline Distributional Reinforcement Learning | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

651 | Self-Consistent Models and Values | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

652 | Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

653 | TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up | 6.75 | 0.83 | 6, 7, 6, 8 | Poster | Poster | |

654 | Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

655 | Invariant Causal Imitation Learning for Generalizable Policies | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

656 | Neural Production Systems | 6.75 | 0.83 | 6, 8, 7, 6 | Poster | Poster | |

657 | Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

658 | CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions | 6.75 | 1.30 | 6, 8, 8, 5 | Poster | Poster | |

659 | FINE Samples for Learning with Noisy Labels | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

660 | Efficient and Local Parallel Random Walks | 6.75 | 1.09 | 8, 7, 5, 7 | Poster | Poster | |

661 | Transformers Generalize DeepSets and Can be Extended to Graphs & Hypergraphs | 6.75 | 0.83 | 8, 7, 6, 6 | Poster | Poster | |

662 | Localization, Convexity, and Star Aggregation | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | |

663 | Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

664 | Terra: Imperative-Symbolic Co-Execution of Imperative Deep Learning Programs | 6.75 | 1.48 | 9, 5, 7, 6 | Poster | Poster | |

665 | Action-guided 3D Human Motion Prediction | 6.75 | 0.83 | 7, 8, 6, 6 | Poster | Poster | |

666 | Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

667 | Few-Round Learning for Federated Learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

668 | A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

669 | Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

670 | Dangers of Bayesian Model Averaging under Covariate Shift | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | ✔ |

671 | Dangers of Bayesian Model Averaging under Covariate Shift | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | ✔ |

672 | Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

673 | A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

674 | Differentially Private Federated Bayesian Optimization with Distributed Exploration | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | ✔ |

675 | Graph Adversarial Self-Supervised Learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

676 | Dynamic Inference with Neural Interpreters | 6.75 | 0.83 | 8, 6, 7, 6 | Poster | Poster | |

677 | The Difficulty of Passive Learning in Deep Reinforcement Learning | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

678 | What training reveals about neural network complexity | 6.75 | 1.30 | 6, 5, 8, 8 | Poster | Poster | ✔ |

679 | On UMAP's True Loss Function | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

680 | Rethinking conditional GAN training: An approach using geometrically structured latent manifolds | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

681 | Scalable Quasi-Bayesian Inference for Instrumental Variable Regression | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

682 | Identity testing for Mallows model | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

683 | Online Learning in Periodic Zero-Sum Games | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

684 | Low-Fidelity Video Encoder Optimization for Temporal Action Localization | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | ✔ |

685 | CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Spotlight | ✔ |

686 | Twice regularized MDPs and the equivalence between robustness and regularization | 6.75 | 1.09 | 8, 7, 7, 5 | Poster | Poster | |

687 | Last-iterate Convergence in Extensive-Form Games | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

688 | COMBO: Conservative Offline Model-Based Policy Optimization | 6.75 | 0.83 | 6, 7, 6, 8 | Poster | Poster | |

689 | Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

690 | Learning to Generate Visual Questions with Noisy Supervision | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Spotlight | ✔ |

691 | Controlling Neural Networks with Rule Representations | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

692 | On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

693 | Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases | 6.75 | 1.09 | 8, 5, 7, 7 | Poster | Poster | ✔ |

694 | Generalized Linear Bandits with Local Differential Privacy | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | ✔ |

695 | Taxonomizing local versus global structure in neural network loss landscapes | 6.75 | 0.83 | 7, 6, 6, 8 | Poster | Poster | |

696 | Interpreting Representation Quality of DNNs for 3D Point Cloud Processing | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

697 | Provably efficient, succinct, and precise explanations | 6.75 | 1.30 | 8, 8, 5, 6 | Poster | Reject | ✔ |

698 | Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning | 6.75 | 0.83 | 6, 8, 7, 6 | Poster | Poster | ✔ |

699 | CoAtNet: Marrying Convolution and Attention for All Data Sizes | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | ✔ |

700 | Memory-efficient Patch-based Inference for Tiny Deep Learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

701 | Robust Regression Revisited: Acceleration and Improved Estimation Rates | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

702 | Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis | 6.75 | 1.64 | 8, 4, 8, 7 | Poster | Poster | |

703 | Efficient Algorithms for Learning Depth-2 Neural Networks with General ReLU Activations | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

704 | Compressive Visual Representations | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

705 | Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation | 6.75 | 1.79 | 7, 9, 7, 4 | Poster | Poster | |

706 | Residual2Vec: Debiasing graph embedding with random graphs | 6.75 | 0.83 | 7, 8, 6, 6 | Poster | Spotlight | ✔ |

707 | Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

708 | Dimensionality Reduction for Wasserstein Barycenter | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | ✔ |

709 | Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | |

710 | Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling | 6.75 | 1.09 | 5, 8, 7, 7 | Poster | Poster | |

711 | Combining Human Predictions with Model Probabilities via Confusion Matrices and Calibration | 6.75 | 1.09 | 8, 7, 7, 5 | Poster | Poster | |

712 | Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning | 6.75 | 0.83 | 6, 8, 7, 6 | Poster | Poster | |

713 | An Uncertainty Principle is a Price of Privacy-Preserving Microdata | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Spotlight | ✔ |

714 | Neural Active Learning with Performance Guarantees | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

715 | Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

716 | Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

717 | Achieving Rotational Invariance with Bessel-Convolutional Neural Networks | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | ✔ |

718 | Visualizing the Emergence of Intermediate Visual Patterns in DNNs | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

719 | Adaptive Diffusion in Graph Neural Networks | 6.75 | 0.83 | 6, 6, 7, 8 | Poster | Poster | |

720 | Noisy Adaptation Generates Lévy Flights in Attractor Neural Networks | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

721 | Periodic Activation Functions Induce Stationarity | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | ✔ |

722 | Periodic Activation Functions Induce Stationarity | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | ✔ |

723 | Learning Conjoint Attentions for Graph Neural Nets | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

724 | Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

725 | Improving Contrastive Learning on Imbalanced Data via Open-World Sampling | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

726 | Implicit Semantic Response Alignment for Partial Domain Adaptation | 6.75 | 1.30 | 8, 8, 6, 5 | Poster | Poster | |

727 | Differentially Private Multi-Armed Bandits in the Shuffle Model | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | ✔ |

728 | A Constant Approximation Algorithm for Sequential Random-Order No-Substitution k-Median Clustering | 6.75 | 1.09 | 7, 7, 5, 8 | Poster | Poster | |

729 | Explicit loss asymptotics in the gradient descent training of neural networks | 6.75 | 0.83 | 8, 7, 6, 6 | Poster | Poster | |

730 | A Probabilistic State Space Model for Joint Inference from Differential Equations and Data | 6.75 | 0.83 | 7, 6, 8, 6 | Poster | Poster | |

731 | On the Importance of Gradients for Detecting Distributional Shifts in the Wild | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | |

732 | Can multi-label classification networks know what they don’t know? | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

733 | Contrastive Active Inference | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

734 | Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation | 6.75 | 0.83 | 7, 6, 6, 8 | Poster | Poster | |

735 | The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization | 6.75 | 0.83 | 6, 8, 7, 6 | Poster | Poster | |

736 | Optimality of variational inference for stochasticblock model with missing links | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

737 | Differentiable Simulation of Soft Multi-body Systems | 6.75 | 0.43 | 7, 6, 7, 7 | Poster | Poster | |

738 | SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | ✔ |

739 | MarioNette: Self-Supervised Sprite Learning | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

740 | Learning to Learn Graph Topologies | 6.75 | 0.83 | 8, 6, 6, 7 | Poster | Poster | |

741 | When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

742 | No RL, No Simulation: Learning to Navigate without Navigating | 6.75 | 1.09 | 5, 7, 8, 7 | Poster | Poster | |

743 | Learning One Representation to Optimize All Rewards | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Poster | |

744 | Certifying Robustness to Programmable Data Bias in Decision Trees | 6.75 | 0.83 | 6, 6, 8, 7 | Poster | Poster | |

745 | SNIPS: Solving Noisy Inverse Problems Stochastically | 6.75 | 1.09 | 7, 7, 8, 5 | Poster | Spotlight | ✔ |

746 | Counterexample Guided RL Policy Refinement Using Bayesian Optimization | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

747 | Dimension-free empirical entropy estimation | 6.75 | 0.43 | 6, 7, 7, 7 | Poster | Poster | |

748 | Mining the Benefits of Two-stage and One-stage HOI Detection | 6.75 | 0.83 | 6, 7, 8, 6 | Poster | Poster | |

749 | Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training | 6.75 | 0.83 | 7, 6, 8, 6 | Poster | Poster | |

750 | Deep Contextual Video Compression | 6.75 | 1.09 | 5, 7, 7, 8 | Poster | Poster | |

751 | Provable Representation Learning for Imitation with Contrastive Fourier Features | 6.75 | 0.43 | 7, 7, 7, 6 | Poster | Poster | |

752 | Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure | 6.75 | 0.43 | 7, 7, 6, 7 | Poster | Poster | |

753 | Exploring the Limits of Out-of-Distribution Detection | 6.75 | 0.83 | 6, 8, 6, 7 | Poster | Poster | |

754 | Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation | 6.75 | 0.43 | 7, 7, 6, 7 | Spotlight | Spotlight | ✔ |

755 | Variational Bayesian Optimistic Sampling | 6.75 | 0.43 | 7, 6, 7, 7 | Spotlight | Spotlight | |

756 | Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems | 6.75 | 0.43 | 7, 6, 7, 7 | Spotlight | Spotlight | |

757 | Sequence-to-Sequence Learning with Latent Neural Grammars | 6.75 | 0.83 | 6, 7, 8, 6 | Spotlight | Poster | ✔ |

758 | Regulating algorithmic filtering on social media | 6.75 | 1.48 | 7, 9, 5, 6 | Spotlight | Spotlight | |

759 | Embedding Principle of Loss Landscape of Deep Neural Networks | 6.75 | 0.43 | 7, 6, 7, 7 | Spotlight | Spotlight | |

760 | Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning | 6.75 | 0.43 | 7, 7, 7, 6 | Spotlight | Spotlight | |

761 | Reward is enough for convex MDPs | 6.75 | 0.43 | 6, 7, 7, 7 | Spotlight | Spotlight | |

762 | Learning to See by Looking at Noise | 6.75 | 0.83 | 6, 8, 6, 7 | Spotlight | Spotlight | |

763 | Improved Coresets and Sublinear Algorithms for Power Means in Euclidean Spaces | 6.75 | 0.83 | 6, 8, 7, 6 | Spotlight | Spotlight | |

764 | Neural Scene Flow Prior | 6.75 | 0.43 | 6, 7, 7, 7 | Spotlight | Spotlight | |

765 | Slice Sampling Reparameterization Gradients | 6.75 | 0.43 | 7, 7, 6, 7 | Spotlight | Spotlight | |

766 | Probabilistic Attention for Interactive Segmentation | 6.75 | 0.43 | 7, 6, 7, 7 | Spotlight | Spotlight | |

767 | Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms | 6.75 | 0.43 | 7, 6, 7, 7 | Spotlight | Spotlight | |

768 | Techniques for Symbol Grounding with SATNet | 6.75 | 1.48 | 9, 5, 7, 6 | Spotlight | Spotlight | |

769 | Parametric Complexity Bounds for Approximating PDEs with Neural Networks | 6.75 | 0.83 | 6, 8, 7, 6 | Spotlight | Spotlight | |

770 | Practical Near Neighbor Search via Group Testing | 6.75 | 0.83 | 8, 6, 6, 7 | Spotlight | Spotlight | |

771 | Refining Language Models with Compositional Explanations | 6.75 | 0.43 | 7, 7, 6, 7 | Spotlight | Spotlight | |

772 | An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence | 6.75 | 0.83 | 6, 8, 7, 6 | Spotlight | Poster | ✔ |

773 | TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation | 6.75 | 0.43 | 6, 7, 7, 7 | Spotlight | Spotlight | |

774 | Mixability made efficient: Fast online multiclass logistic regression | 6.75 | 0.43 | 7, 7, 7, 6 | Spotlight | Spotlight | |

775 | A Minimalist Approach to Offline Reinforcement Learning | 6.75 | 1.09 | 8, 5, 7, 7 | Spotlight | Spotlight | |

776 | Pruning Randomly Initialized Neural Networks with Iterative Randomization | 6.75 | 0.43 | 6, 7, 7, 7 | Spotlight | Spotlight | |

777 | Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD | 6.75 | 0.83 | 6, 6, 7, 8 | Spotlight | Spotlight | |

778 | Towards optimally abstaining from prediction with OOD test examples | 6.75 | 0.83 | 8, 6, 6, 7 | Spotlight | Spotlight | |

779 | Across-animal odor decoding by probabilistic manifold alignment | 6.75 | 0.83 | 8, 6, 7, 6 | Spotlight | Spotlight | |

780 | On Linear Stability of SGD and Input-Smoothness of Neural Networks | 6.75 | 0.83 | 6, 7, 8, 6 | Spotlight | Spotlight | |

781 | Deep Self-Dissimilarities as Powerful Visual Fingerprints | 6.75 | 0.83 | 8, 7, 6, 6 | Spotlight | Spotlight | |

782 | Bias and variance of the Bayesian-mean decoder | 6.75 | 0.83 | 7, 8, 6, 6 | Spotlight | Spotlight | |

783 | Decentralized Learning in Online Queuing Systems | 6.75 | 1.09 | 7, 8, 5, 7 | Spotlight | Spotlight | |

784 | Neural Additive Models: Interpretable Machine Learning with Neural Nets | 6.75 | 1.09 | 7, 5, 7, 8 | Spotlight | Spotlight | |

785 | Understanding the Under-Coverage Bias in Uncertainty Estimation | 6.75 | 0.83 | 6, 7, 8, 6 | Spotlight | Spotlight | |

786 | Exact marginal prior distributions of finite Bayesian neural networks | 6.75 | 0.83 | 6, 8, 6, 7 | Spotlight | Spotlight | |

787 | The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning | 6.75 | 0.83 | 6, 6, 7, 8 | Spotlight | Spotlight | |

788 | α
-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression | 6.71 | 0.45 | 7, 7, 7, 7, 7, 6, 6 | Poster | Poster | ✔ |

789 | Instance-Dependent Bounds for Zeroth-order Lipschitz Optimization with Error Certificates | 6.71 | 0.45 | 6, 7, 7, 7, 7, 7, 6 | Poster | Poster | |

790 | Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons | 6.67 | 2.62 | 3, 8, 9 | Oral | Poster | ✔ |

791 | Understanding the Generalization Benefit of Model Invariance from a Data Perspective | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

792 | Decoupling the Depth and Scope of Graph Neural Networks | 6.67 | 1.70 | 5, 9, 6 | Poster | Poster | ✔ |

793 | Beware of the Simulated DAG! Causal Discovery Benchmarks May Be Easy to Game | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

794 | Asynchronous Decentralized Online Learning | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

795 | Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space | 6.67 | 1.49 | 9, 8, 5, 6, 5, 7 | Poster | Poster | ✔ |

796 | Efficient Truncated Linear Regression with Unknown Noise Variance | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

797 | Federated Graph Classification over Non-IID Graphs | 6.67 | 1.89 | 8, 8, 4 | Poster | Poster | |

798 | Shapeshifter: a Parameter-efficient Transformer using Factorized Reshaped Matrices | 6.67 | 0.47 | 7, 7, 7, 6, 7, 6 | Poster | Poster | |

799 | Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

800 | On the Generative Utility of Cyclic Conditionals | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | |

801 | Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

802 | Learning Debiased and Disentangled Representations for Semantic Segmentation | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

803 | Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

804 | Continuous Mean-Covariance Bandits | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | ✔ |

805 | All Tokens Matter: Token Labeling for Training Better Vision Transformers | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

806 | Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | ✔ |

807 | PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | ✔ |

808 | Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

809 | Luna: Linear Unified Nested Attention | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

810 | Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | ✔ |

811 | Learning Semantic Representations to Verify Hardware Designs | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

812 | Efficient Generalization with Distributionally Robust Learning | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | |

813 | Few-Shot Data-Driven Algorithms for Low Rank Approximation | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

814 | STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | ✔ |

815 | Relational Self-Attention: What's Missing in Attention for Video Understanding | 6.67 | 0.47 | 7, 6, 7 | Poster | Spotlight | ✔ |

816 | Good Classification Measures and How to Find Them | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

817 | Synthetic Design: An Optimization Approach to Experimental Design with Synthetic Controls | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

818 | The Adaptive Doubly Robust Estimator and a Paradox Concerning Logging Policy | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

819 | Safe Reinforcement Learning by Imagining the Near Future | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | |

820 | Accelerating Quadratic Optimization with Reinforcement Learning | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | ✔ |

821 | Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

822 | Towards Instance-Optimal Offline Reinforcement Learning with Pessimism | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

823 | Multi-Scale Representation Learning on Proteins | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

824 | Near-Optimal Offline Reinforcement Learning via Double Variance Reduction | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

825 | AC-GC: Lossy Activation Compression with Guaranteed Convergence | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

826 | SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training using Gradient Similarity Measurement | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

827 | Convergence of adaptive algorithms for constrained weakly convex optimization | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

828 | NeuroMLR: Robust & Reliable Route Recommendation on Road Networks | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | |

829 | The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

830 | Proportional Participatory Budgeting with Additive Utilities | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

831 | Streaming Belief Propagation for Community Detection | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | ✔ |

832 | Biological key-value memory networks | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | ✔ |

833 | Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

834 | Bandits with many optimal arms | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | |

835 | NN-Baker: A Neural-network Infused Algorithmic Framework for Optimization Problems on Geometric Intersection Graphs | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

836 | Reliable Post hoc Explanations: Modeling Uncertainty in Explainability | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | ✔ |

837 | Probabilistic Forecasting: A Level-Set Approach | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

838 | Local Disentanglement in Variational Auto-Encoders Using Jacobian
L1
Regularization | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

839 | Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

840 | Differentially Private Empirical Risk Minimization under the Fairness Lens | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

841 | MagNet: A Neural Network for Directed Graphs | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

842 | Adversarial Intrinsic Motivation for Reinforcement Learning | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

843 | Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

844 | Garment4D: Garment Reconstruction from Point Cloud Sequences | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

845 | Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

846 | Independent Prototype Propagation for Zero-Shot Compositionality | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

847 | DualNet: Continual Learning, Fast and Slow | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

848 | What Matters for Adversarial Imitation Learning? | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

849 | Representation Learning on Spatial Networks | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

850 | Privately Learning Mixtures of Axis-Aligned Gaussians | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

851 | Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

852 | Towards mental time travel: a hierarchical memory for reinforcement learning agents | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

853 | Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

854 | Object-aware Contrastive Learning for Debiased Scene Representation | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

855 | Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

856 | Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings | 6.67 | 0.47 | 7, 6, 7 | Poster | Spotlight | ✔ |

857 | Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

858 | Curriculum Disentangled Recommendation with Noisy Multi-feedback | 6.67 | 1.25 | 8, 7, 5 | Poster | Poster | |

859 | Collaborative Uncertainty in Multi-Agent Trajectory Forecasting | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

860 | Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

861 | A Faster Maximum Cardinality Matching Algorithm with Applications in Machine Learning | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

862 | The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

863 | Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | ✔ |

864 | Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

865 | Streaming Linear System Identification with Reverse Experience Replay | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

866 | Loss function based second-order Jensen inequality and its application to particle variational inference | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

867 | Risk Bounds and Calibration for a Smart Predict-then-Optimize Method | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

868 | Provably efficient, succinct, and precise explanations | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | ✔ |

869 | Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

870 | Perturbation Theory for the Information Bottleneck | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

871 | Adversarial Robustness of Streaming Algorithms through Importance Sampling | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

872 | Learning to Combine Per-Example Solutions for Neural Program Synthesis | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

873 | Scalable Online Planning via Reinforcement Learning Fine-Tuning | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

874 | Private and Non-private Uniformity Testing for Ranking Data | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | ✔ |

875 | Improved Regret Bounds for Tracking Experts with Memory | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | ✔ |

876 | Representing Hyperbolic Space Accurately using Multi-Component Floats | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

877 | Disrupting Deep Uncertainty Estimation Without Harming Accuracy | 6.67 | 0.47 | 7, 6, 7 | Poster | Spotlight | ✔ |

878 | On Margin-Based Cluster Recovery with Oracle Queries | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

879 | Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks | 6.67 | 1.70 | 9, 5, 6 | Poster | Poster | |

880 | UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | |

881 | Uncertainty-Driven Loss for Single Image Super-Resolution | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | ✔ |

882 | Robustifying Algorithms of Learning Latent Trees with Vector Variables | 6.67 | 1.25 | 5, 7, 8 | Poster | Poster | |

883 | Adversarially Robust Change Point Detection | 6.67 | 0.94 | 8, 6, 6 | Poster | Poster | ✔ |

884 | Heavy Ball Neural Ordinary Differential Equations | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

885 | The Elastic Lottery Ticket Hypothesis | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

886 | Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

887 | Reverse-Complement Equivariant Networks for DNA Sequences | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

888 | On Effective Scheduling of Model-based Reinforcement Learning | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

889 | BCORLE(
λ
): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | ✔ |

890 | Learning Graph Cellular Automata | 6.67 | 0.94 | 6, 6, 8 | Poster | Poster | |

891 | Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks | 6.67 | 0.94 | 6, 8, 6 | Poster | Poster | |

892 | Curriculum Offline Imitating Learning | 6.67 | 0.47 | 7, 6, 7 | Poster | Poster | |

893 | Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors | 6.67 | 0.47 | 7, 7, 6 | Poster | Poster | |

894 | Self-Supervised Bug Detection and Repair | 6.67 | 0.47 | 6, 7, 7 | Poster | Poster | ✔ |

895 | Subgraph Federated Learning with Missing Neighbor Generation | 6.67 | 0.94 | 6, 8, 6 | Spotlight | Spotlight | |

896 | Property-Aware Relation Networks for Few-Shot Molecular Property Prediction | 6.67 | 0.94 | 8, 6, 6 | Spotlight | Spotlight | |

897 | Uncertain Decisions Facilitate Better Preference Learning | 6.67 | 0.47 | 7, 6, 7 | Spotlight | Spotlight | |

898 | Lower and Upper Bounds on the Pseudo-Dimension of Tensor Network Models | 6.67 | 0.47 | 6, 7, 7 | Spotlight | Spotlight | |

899 | Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks | 6.67 | 0.47 | 7, 6, 7 | Spotlight | Spotlight | ✔ |

900 | Learning with Holographic Reduced Representations | 6.67 | 0.47 | 7, 6, 7 | Spotlight | Poster | ✔ |

901 | Tensor Normal Training for Deep Learning Models | 6.67 | 0.47 | 7, 6, 7 | Spotlight | Spotlight | |

902 | Statistical Regeneration Guarantees of the Wasserstein Autoencoder with Latent Space Consistency | 6.67 | 0.47 | 7, 7, 6 | Spotlight | Spotlight | |

903 | Provably Faster Algorithms for Bilevel Optimization | 6.67 | 0.47 | 6, 7, 7 | Spotlight | Spotlight | |

904 | Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality | 6.67 | 0.94 | 6, 8, 6 | Spotlight | Spotlight | |

905 | Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization | 6.67 | 0.47 | 6, 7, 7 | Spotlight | Spotlight | |

906 | Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach | 6.67 | 0.47 | 7, 6, 7 | Spotlight | Spotlight | |

907 | On Inductive Biases for Heterogeneous Treatment Effect Estimation | 6.67 | 0.94 | 6, 6, 8 | Spotlight | Spotlight | |

908 | Coresets for Decision Trees of Signals | 6.67 | 0.47 | 7, 7, 6 | Spotlight | Poster | ✔ |

909 | Revisiting ResNets: Improved Training and Scaling Strategies | 6.67 | 0.94 | 8, 6, 6 | Spotlight | Spotlight | |

910 | Kernel Functional Optimisation | 6.60 | 1.36 | 5, 7, 5, 8, 8 | Poster | Poster | |

911 | Learnability of Linear Thresholds from Label Proportions | 6.60 | 0.80 | 7, 7, 7, 7, 5 | Poster | Poster | |

912 | Progressive Feature Interaction Search for Deep Sparse Network | 6.60 | 0.49 | 6, 7, 6, 7, 7 | Poster | Poster | |

913 | Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding | 6.60 | 0.80 | 6, 6, 7, 6, 8 | Poster | Poster | |

914 | Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems | 6.60 | 1.02 | 5, 6, 7, 7, 8 | Poster | Poster | |

915 | Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations | 6.60 | 0.49 | 6, 7, 7, 6, 7 | Poster | Poster | |

916 | ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs | 6.60 | 0.80 | 6, 6, 7, 6, 8 | Poster | Poster | |

917 | Entropic Desired Dynamics for Intrinsic Control | 6.60 | 0.49 | 7, 6, 6, 7, 7 | Poster | Poster | ✔ |

918 | Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits | 6.60 | 0.80 | 6, 6, 7, 6, 8 | Poster | Poster | |

919 | Scaling Neural Tangent Kernels via Sketching and Random Features | 6.60 | 0.49 | 7, 6, 7, 7, 6 | Poster | Poster | ✔ |

920 | No-Press Diplomacy from Scratch | 6.60 | 0.80 | 7, 6, 8, 6, 6 | Poster | Poster | |

921 | Implicit Transformer Network for Screen Content Image Continuous Super-Resolution | 6.60 | 0.80 | 7, 7, 5, 7, 7 | Poster | Poster | |

922 | What training reveals about neural network complexity | 6.60 | 0.49 | 6, 7, 7, 7, 6 | Poster | Poster | ✔ |

923 | Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning | 6.60 | 0.49 | 7, 6, 7, 7, 6 | Poster | Poster | |

924 | A Comprehensively Tight Analysis of Gradient Descent for PCA | 6.60 | 0.80 | 6, 6, 8, 7, 6 | Poster | Poster | |

925 | Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media | 6.60 | 1.50 | 8, 8, 6, 7, 4 | Poster | Poster | |

926 | Variational Continual Bayesian Meta-Learning | 6.60 | 0.49 | 7, 6, 7, 6, 7 | Poster | Poster | |

927 | Optimal Underdamped Langevin MCMC Method | 6.57 | 1.05 | 7, 7, 7, 8, 5, 5, 7 | Poster | Poster | |

928 | Data driven semi-supervised learning | 6.50 | 1.66 | 8, 4, 6, 8 | Oral | Oral | |

929 | Adaptive wavelet distillation from neural networks through interpretations | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

930 | Adaptive Risk Minimization: Learning to Adapt to Domain Shift | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

931 | Functional Regularization for Reinforcement Learning via Learned Fourier Features | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

932 | Multi-Step Budgeted Bayesian Optimization with Unknown Evaluation Costs | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

933 | On the Representation Power of Set Pooling Networks | 6.50 | 0.76 | 6, 6, 6, 8, 6, 7 | Poster | Poster | |

934 | Attention Approximates Sparse Distributed Memory | 6.50 | 1.12 | 8, 6, 7, 5 | Poster | Poster | |

935 | Compositional Transformers for Scene Generation | 6.50 | 1.12 | 8, 5, 7, 6 | Poster | Poster | |

936 | SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

937 | Functional Variational Inference based on Stochastic Process Generators | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

938 | Emergent Communication under Varying Sizes and Connectivities | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

939 | Stochastic optimization under time drift: iterate averaging, step-decay schedules, and high probability guarantees | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

940 | Noether Networks: meta-learning useful conserved quantities | 6.50 | 0.87 | 7, 7, 7, 5 | Poster | Poster | |

941 | Baby Intuitions Benchmark (BIB): Discerning the goals, preferences, and actions of others | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

942 | On Optimal Robustness to Adversarial Corruption in Online Decision Problems | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

943 | A Kernel-based Test of Independence for Cluster-correlated Data | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

944 | Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz Requirements | 6.50 | 1.12 | 6, 7, 5, 8 | Poster | Poster | |

945 | Improving black-box optimization in VAE latent space using decoder uncertainty | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

946 | Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

947 | Rebounding Bandits for Modeling Satiation Effects | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

948 | VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media | 6.50 | 0.87 | 7, 7, 7, 5 | Poster | Poster | ✔ |

949 | Debiased Visual Question Answering from Feature and Sample Perspectives | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

950 | PortaSpeech: Portable and High-Quality Generative Text-to-Speech | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

951 | Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training | 6.50 | 1.12 | 6, 7, 8, 5 | Poster | Poster | |

952 | Unsupervised Foreground Extraction via Deep Region Competition | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

953 | CANITA: Faster Rates for Distributed Convex Optimization with Communication Compression | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

954 | Dynamic Resolution Network | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

955 | Model Selection for Bayesian Autoencoders | 6.50 | 1.66 | 6, 8, 4, 8 | Poster | Poster | |

956 | Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

957 | Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

958 | Perturb-and-max-product: Sampling and learning in discrete energy-based models | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

959 | Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | ✔ |

960 | A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

961 | Fair Scheduling for Time-dependent Resources | 6.50 | 1.50 | 7, 8, 4, 7 | Poster | Poster | |

962 | Explainable Semantic Space by Grounding Language to Vision with Cross-Modal Contrastive Learning | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

963 | Generalization Bounds for Graph Embedding Using Negative Sampling: Linear vs Hyperbolic | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

964 | Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

965 | Towards Stable and Robust AdderNets | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

966 | Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks | 6.50 | 1.12 | 5, 6, 8, 7 | Poster | Spotlight | ✔ |

967 | Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

968 | Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | ✔ |

969 | Self-Adaptable Point Processes with Nonparametric Time Decays | 6.50 | 0.87 | 8, 6, 6, 6 | Poster | Poster | |

970 | Improving Robustness using Generated Data | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

971 | Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

972 | Characterizing the risk of fairwashing | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

973 | Fast Pure Exploration via Frank-Wolfe | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | ✔ |

974 | Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

975 | Projected GANs Converge Faster | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

976 | Pseudo-Spherical Contrastive Divergence | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

977 | Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | ✔ |

978 | Choose a Transformer: Fourier or Galerkin | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

979 | Fair Classification with Adversarial Perturbations | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

980 | Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning | 6.50 | 1.50 | 7, 4, 7, 8 | Poster | Poster | |

981 | Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

982 | Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

983 | Mastering Atari Games with Limited Data | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

984 | Symbolic Regression via Deep Reinforcement Learning Enhanced Genetic Programming Seeding | 6.50 | 1.50 | 6, 9, 5, 6 | Poster | Poster | |

985 | Joint Inference for Neural Network Depth and Dropout Regularization | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

986 | Adversarial Robustness with Non-uniform Perturbations | 6.50 | 0.50 | 7, 6, 6, 6, 7, 7 | Poster | Poster | ✔ |

987 | VoiceMixer: Adversarial Voice Style Mixup | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | ✔ |

988 | Shifted Chunk Transformer for Spatio-Temporal Representational Learning | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

989 | Machine versus Human Attention in Deep Reinforcement Learning Tasks | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | ✔ |

990 | Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

991 | Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

992 | Online Robust Reinforcement Learning with Model Uncertainty | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

993 | Learning to Predict Trustworthiness with Steep Slope Loss | 6.50 | 1.12 | 5, 8, 6, 7 | Poster | Poster | |

994 | Privately Learning Subspaces | 6.50 | 1.12 | 5, 8, 6, 7 | Poster | Poster | |

995 | Average-Reward Learning and Planning with Options | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | ✔ |

996 | SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

997 | ErrorCompensatedX: error compensation for variance reduced algorithms | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | ✔ |

998 | Do Vision Transformers See Like Convolutional Neural Networks? | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Spotlight | ✔ |

999 | Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1000 | GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

1001 | Diversity Matters When Learning From Ensembles | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

1002 | Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1003 | Duplex Sequence-to-Sequence Learning for Reversible Machine Translation | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1004 | HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1005 | Stochastic Solutions for Linear Inverse Problems using the Prior Implicit in a Denoiser | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1006 | D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1007 | A/B Testing for Recommender Systems in a Two-sided Marketplace | 6.50 | 1.12 | 7, 5, 8, 6 | Poster | Poster | |

1008 | Fast Certified Robust Training with Short Warmup | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | ✔ |

1009 | Coupled Gradient Estimators for Discrete Latent Variables | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | ✔ |

1010 | Sparse Flows: Pruning Continuous-depth Models | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1011 | SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1012 | Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1013 | Margin-Independent Online Multiclass Learning via Convex Geometry | 6.50 | 0.87 | 7, 5, 7, 7 | Poster | Poster | |

1014 | Online learning in MDPs with linear function approximation and bandit feedback. | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1015 | Capacity and Bias of Learned Geometric Embeddings for Directed Graphs | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1016 | LEADS: Learning Dynamical Systems that Generalize Across Environments | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1017 | Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1018 | Generalization Bounds for (Wasserstein) Robust Optimization | 6.50 | 1.80 | 9, 6, 4, 7 | Poster | Poster | |

1019 | Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis | 6.50 | 1.12 | 8, 5, 6, 7 | Poster | Poster | |

1020 | Causal Inference for Event Pairs in Multivariate Point Processes | 6.50 | 1.12 | 8, 6, 7, 5 | Poster | Poster | |

1021 | BooVAE: Boosting Approach for Continual Learning of VAE | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1022 | Risk-Aware Transfer in Reinforcement Learning using Successor Features | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1023 | Dynamics-regulated kinematic policy for egocentric pose estimation | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1024 | Panoptic 3D Scene Reconstruction From a Single RGB Image | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1025 | Revisiting Model Stitching to Compare Neural Representations | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1026 | Can fMRI reveal the representation of syntactic structure in the brain? | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1027 | Teachable Reinforcement Learning via Advice Distillation | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1028 | Fairness in Ranking under Uncertainty | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1029 | Reverse engineering learned optimizers reveals known and novel mechanisms | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1030 | A Gang of Adversarial Bandits | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1031 | Implicit Sparse Regularization: The Impact of Depth and Early Stopping | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1032 | An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1033 | Reinforcement Learning with State Observation Costs in Action-Contingent Noiselessly Observable Markov Decision Processes | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1034 | Off-Policy Risk Assessment in Contextual Bandits | 6.50 | 1.12 | 7, 8, 5, 6 | Poster | Poster | |

1035 | Learning Models for Actionable Recourse | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1036 | Latent Matters: Learning Deep State-Space Models | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1037 | Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1038 | Multiclass Boosting and the Cost of Weak Learning | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | ✔ |

1039 | An Online Riemannian PCA for Stochastic Canonical Correlation Analysis | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1040 | Overlapping Spaces for Compact Graph Representations | 6.50 | 0.87 | 7, 5, 7, 7 | Poster | Poster | |

1041 | Regret Bounds for Gaussian-Process Optimization in Large Domains | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1042 | Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1043 | Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

1044 | Robust Deep Reinforcement Learning through Adversarial Loss | 6.50 | 2.18 | 7, 7, 9, 3 | Poster | Poster | |

1045 | Rethinking Graph Transformers with Spectral Attention | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1046 | Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | ✔ |

1047 | Sifting through the noise: Universal first-order methods for stochastic variational inequalities | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1048 | Causal Abstractions of Neural Networks | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1049 | A Causal Lens for Controllable Text Generation | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1050 | The effectiveness of feature attribution methods and its correlation with automatic evaluation scores | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1051 | Sparse is Enough in Scaling Transformers | 6.50 | 1.12 | 6, 8, 5, 7 | Poster | Poster | |

1052 | On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay | 6.50 | 0.87 | 7, 5, 7, 7 | Poster | Poster | |

1053 | Neural Dubber: Dubbing for Videos According to Scripts | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1054 | Densely connected normalizing flows | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1055 | Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1056 | Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1057 | Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1058 | Strategic Behavior is Bliss: Iterative Voting Improves Social Welfare | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1059 | Adaptive Machine Unlearning | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

1060 | Bandit Learning with Delayed Impact of Actions | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | ✔ |

1061 | A Continuous Mapping For Augmentation Design | 6.50 | 1.50 | 4, 7, 8, 7 | Poster | Poster | |

1062 | Deep Networks Provably Classify Data on Curves | 6.50 | 1.66 | 8, 6, 4, 8 | Poster | Poster | ✔ |

1063 | Deep Networks Provably Classify Data on Curves | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | ✔ |

1064 | Pointwise Bounds for Distribution Estimation under Communication Constraints | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1065 | Online Facility Location with Multiple Advice | 6.50 | 1.12 | 5, 6, 7, 8 | Poster | Poster | |

1066 | Nested Variational Inference | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | ✔ |

1067 | T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1068 | RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1069 | A novel notion of barycenter for probability distributions based on optimal weak mass transport | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1070 | Neural Trees for Learning on Graphs | 6.50 | 1.50 | 4, 8, 7, 7 | Poster | Poster | |

1071 | Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1072 | Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1073 | Consistency Regularization for Variational Auto-Encoders | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1074 | Low-dimensional Structure in the Space of Language Representations is Reflected in Brain Responses | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1075 | Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1076 | Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | ✔ |

1077 | Clockwork Variational Autoencoders | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1078 | An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1079 | PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1080 | On sensitivity of meta-learning to support data | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1081 | Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1082 | Submodular + Concave | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1083 | A first-order primal-dual method with adaptivity to local smoothness | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1084 | The Skellam Mechanism for Differentially Private Federated Learning | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1085 | Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1086 | Encoding Robustness to Image Style via Adversarial Feature Perturbations | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1087 | Designing Counterfactual Generators using Deep Model Inversion | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1088 | Logarithmic Regret from Sublinear Hints | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1089 | Reliable Post hoc Explanations: Modeling Uncertainty in Explainability | 6.50 | 2.06 | 8, 8, 3, 7 | Poster | Poster | ✔ |

1090 | Instance-Conditional Knowledge Distillation for Object Detection | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1091 | Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1092 | Human-Adversarial Visual Question Answering | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1093 | End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering | 6.50 | 0.87 | 6, 6, 6, 8 | Poster | Poster | |

1094 | Controlled Text Generation as Continuous Optimization with Multiple Constraints | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1095 | Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble | 6.50 | 1.12 | 8, 7, 5, 6 | Poster | Poster | |

1096 | Active Offline Policy Selection | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

1097 | Counterbalancing Learning and Strategic Incentives in Allocation Markets | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1098 | ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

1099 | Understanding Bandits with Graph Feedback | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | ✔ |

1100 | Pay Attention to MLPs | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1101 | Multi-Agent Reinforcement Learning in Stochastic Networked Systems | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1102 | Unsupervised Object-Based Transition Models For 3D Partially Observable Environments | 6.50 | 0.96 | 5, 7, 8, 6, 6, 7 | Poster | Poster | ✔ |

1103 | Learning latent causal graphs via mixture oracles | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1104 | Locality Sensitive Teaching | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1105 | Laplace Redux - Effortless Bayesian Deep Learning | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1106 | Explicable Reward Design for Reinforcement Learning Agents | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1107 | Prior-independent Dynamic Auctions for a Value-maximizing Buyer | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1108 | Robust Implicit Networks via Non-Euclidean Contractions | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1109 | Adversarial Neuron Pruning Purifies Backdoored Deep Models | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1110 | Dynamic Causal Bayesian Optimization | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1111 | CentripetalText: An Efficient Text Instance Representation for Scene Text Detection | 6.50 | 0.87 | 6, 6, 6, 8 | Poster | Poster | |

1112 | Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1113 | Computer-Aided Design as Language | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1114 | Fast Algorithms for
L∞
-constrained S-rectangular Robust MDPs | 6.50 | 1.12 | 6, 7, 5, 8 | Poster | Poster | ✔ |

1115 | Hierarchical Clustering:
O(1)
-Approximation for Well-Clustered Graphs | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1116 | Storchastic: A Framework for General Stochastic Automatic Differentiation | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1117 | Minimizing Polarization and Disagreement in Social Networks via Link Recommendation | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1118 | Shape Registration in the Time of Transformers | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1119 | A Regression Approach to Learning-Augmented Online Algorithms | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1120 | Extracting Deformation-Aware Local Features by Learning to Deform | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1121 | Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1122 | Learning to Simulate Self-driven Particles System with Coordinated Policy Optimization | 6.50 | 1.50 | 8, 7, 4, 7 | Poster | Poster | |

1123 | Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr'om Method | 6.50 | 1.26 | 5, 6, 9, 6, 6, 7 | Poster | Poster | |

1124 | Automatic Data Augmentation for Generalization in Reinforcement Learning | 6.50 | 0.87 | 7, 5, 7, 7 | Poster | Poster | |

1125 | Post-processing for Individual Fairness | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

1126 | Sampling with Trusthworthy Constraints: A Variational Gradient Framework | 6.50 | 0.87 | 8, 6, 6, 6 | Poster | Poster | |

1127 | Deep Learning on a Data Diet: Finding Important Examples Early in Training | 6.50 | 0.87 | 8, 6, 6, 6 | Poster | Poster | |

1128 | Challenges and Opportunities in High Dimensional Variational Inference | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1129 | On the Expected Complexity of Maxout Networks | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1130 | Sageflow: Robust Federated Learning against Both Stragglers and Adversaries | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1131 | Fine-grained Generalization Analysis of Inductive Matrix Completion | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1132 | Regret Minimization Experience Replay in Off-Policy Reinforcement Learning | 6.50 | 2.29 | 8, 9, 3, 6 | Poster | Poster | ✔ |

1133 | Circa: Stochastic ReLUs for Private Deep Learning | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1134 | Learning and Generalization in RNNs | 6.50 | 1.12 | 6, 8, 5, 7 | Poster | Poster | |

1135 | Learning State Representations from Random Deep Action-conditional Predictions | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1136 | Compacter: Efficient Low-Rank Hypercomplex Adapter Layers | 6.50 | 1.50 | 9, 6, 5, 6 | Poster | Poster | |

1137 | Practical Large-Scale Linear Programming using Primal-Dual Hybrid Gradient | 6.50 | 1.12 | 5, 8, 7, 6 | Poster | Poster | |

1138 | On Provable Benefits of Depth in Training Graph Convolutional Networks | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1139 | Differentiable Learning Under Triage | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1140 | NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | ✔ |

1141 | MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1142 | PatchGame: Learning to Signal Mid-level Patches in Referential Games | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1143 | Ising Model Selection Using
ℓ1
-Regularized Linear Regression: A Statistical Mechanics Analysis | 6.50 | 1.12 | 8, 7, 5, 7, 7, 5 | Poster | Poster | |

1144 | Active 3D Shape Reconstruction from Vision and Touch | 6.50 | 1.12 | 5, 8, 7, 6 | Poster | Poster | |

1145 | Accumulative Poisoning Attacks on Real-time Data | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1146 | Searching Parameterized AP Loss for Object Detection | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1147 | De-randomizing MCMC dynamics with the diffusion Stein operator | 6.50 | 0.87 | 7, 7, 7, 5 | Poster | Poster | |

1148 | LeadCache
: Regret-Optimal Caching in Networks | 6.50 | 1.12 | 8, 5, 7, 6 | Poster | Poster | |

1149 | GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1150 | Credal Self-Supervised Learning | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1151 | Relative stability toward diffeomorphisms indicates performance in deep nets | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1152 | RMM: Reinforced Memory Management for Class-Incremental Learning | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1153 | Well-tuned Simple Nets Excel on Tabular Datasets | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1154 | A 3D Generative Model for Structure-Based Drug Design | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1155 | ReLU Regression with Massart Noise | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1156 | Understanding and Improving Early Stopping for Learning with Noisy Labels | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1157 | Learning-Augmented Dynamic Power Management with Multiple States via New Ski Rental Bounds | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | ✔ |

1158 | Lifelong Domain Adaptation via Consolidated Internal Distribution | 6.50 | 0.87 | 7, 5, 7, 7 | Poster | Poster | |

1159 | Efficient Combination of Rematerialization and Offloading for Training DNNs | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1160 | Matrix factorisation and the interpretation of geodesic distance | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1161 | Few-Shot Object Detection via Association and DIscrimination | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1162 | Weisfeiler and Lehman Go Cellular: CW Networks | 6.50 | 1.66 | 8, 4, 6, 8 | Poster | Poster | |

1163 | A Theory of the Distortion-Perception Tradeoff in Wasserstein Space | 6.50 | 1.12 | 5, 8, 7, 6 | Poster | Poster | |

1164 | Risk-Averse Bayes-Adaptive Reinforcement Learning | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | ✔ |

1165 | The Implicit Bias of Minima Stability: A View from Function Space | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1166 | Regime Switching Bandits | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1167 | On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry | 6.50 | 0.87 | 6, 6, 6, 8 | Poster | Poster | |

1168 | Stylized Dialogue Generation with Multi-Pass Dual Learning | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1169 | Adaptive Data Augmentation on Temporal Graphs | 6.50 | 0.87 | 7, 7, 7, 5 | Poster | Poster | |

1170 | Approximating the Permanent with Deep Rejection Sampling | 6.50 | 1.50 | 6, 6, 9, 5 | Poster | Poster | |

1171 | Diversity Enhanced Active Learning with Strictly Proper Scoring Rules | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1172 | Evaluating State-of-the-Art Classification Models Against Bayes Optimality | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | ✔ |

1173 | An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1174 | Learning rule influences recurrent network representations but not attractor structure in decision-making tasks | 6.50 | 1.12 | 7, 6, 8, 5 | Poster | Poster | |

1175 | Truncated Marginal Neural Ratio Estimation | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1176 | A Contrastive Learning Approach for Training Variational Autoencoder Priors | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1177 | Predicting Molecular Conformation via Dynamic Graph Score Matching | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1178 | Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1179 | Differentially Private n-gram Extraction | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1180 | Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization | 6.50 | 1.12 | 5, 6, 7, 8 | Poster | Poster | |

1181 | G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1182 | Learning to Ground Multi-Agent Communication with Autoencoders | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1183 | Local Hyper-Flow Diffusion | 6.50 | 1.12 | 7, 5, 8, 6 | Poster | Poster | |

1184 | Bayesian Adaptation for Covariate Shift | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1185 | Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1186 | A Biased Graph Neural Network Sampler with Near-Optimal Regret | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1187 | Dynamic Trace Estimation | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1188 | Gradient Starvation: A Learning Proclivity in Neural Networks | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

1189 | Out-of-Distribution Generalization in Kernel Regression | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1190 | Understanding Interlocking Dynamics of Cooperative Rationalization | 6.50 | 1.12 | 6, 8, 7, 5 | Poster | Poster | |

1191 | Generalized Proximal Policy Optimization with Sample Reuse | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1192 | Federated Reconstruction: Partially Local Federated Learning | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1193 | NxMTransformer: Semi-Structured Sparsification for Natural Language Understanding via ADMM | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1194 | Understanding Adaptive, Multiscale Temporal Integration In Deep Speech Recognition Systems | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1195 | Tighter Expected Generalization Error Bounds via Wasserstein Distance | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1196 | Statistical Inference with M-Estimators on Adaptively Collected Data | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1197 | Relaxed Marginal Consistency for Differentially Private Query Answering | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1198 | Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose | 6.50 | 1.50 | 7, 7, 4, 8 | Poster | Poster | |

1199 | Private and Non-private Uniformity Testing for Ranking Data | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

1200 | Learning in Non-Cooperative Configurable Markov Decision Processes | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1201 | Learning Riemannian metric for disease progression modeling | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | ✔ |

1202 | Optimal Order Simple Regret for Gaussian Process Bandits | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1203 | Optimal Rates for Nonparametric Density Estimation under Communication Constraints | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1204 | A Critical Look at the Consistency of Causal Estimation with Deep Latent Variable Models | 6.50 | 0.87 | 6, 6, 8, 6 | Poster | Poster | |

1205 | Meta Internal Learning | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1206 | Learning to Time-Decode in Spiking Neural Networks Through the Information Bottleneck | 6.50 | 1.12 | 7, 8, 6, 5 | Poster | Poster | |

1207 | Neural Tangent Kernel Maximum Mean Discrepancy | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

1208 | Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1209 | DOBF: A Deobfuscation Pre-Training Objective for Programming Languages | 6.50 | 1.12 | 5, 8, 6, 7 | Poster | Poster | |

1210 | Beyond Bandit Feedback in Online Multiclass Classification | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | ✔ |

1211 | Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1212 | Dynamic Bottleneck for Robust Self-Supervised Exploration | 6.50 | 0.87 | 8, 6, 6, 6 | Poster | Poster | |

1213 | Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1214 | To The Point: Correspondence-driven monocular 3D category reconstruction | 6.50 | 0.87 | 6, 6, 6, 8 | Poster | Poster | |

1215 | Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1216 | Do Wider Neural Networks Really Help Adversarial Robustness? | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1217 | An Image is Worth More Than a Thousand Words: Towards Disentanglement in The Wild | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1218 | BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1219 | ReSSL: Relational Self-Supervised Learning with Weak Augmentation | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1220 | Dynamic influence maximization | 6.50 | 1.12 | 5, 8, 6, 7 | Poster | Poster | |

1221 | Equivariant Manifold Flows | 6.50 | 1.12 | 5, 7, 8, 6 | Poster | Poster | |

1222 | Model-Based Episodic Memory Induces Dynamic Hybrid Controls | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

1223 | Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1224 | Adversarially Robust Change Point Detection | 6.50 | 1.50 | 7, 7, 4, 8 | Poster | Poster | ✔ |

1225 | Understanding Deflation Process in Over-parametrized Tensor Decomposition | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

1226 | Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1227 | EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1228 | Automatic Unsupervised Outlier Model Selection | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1229 | Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1230 | On the Convergence of Step Decay Step-Size for Stochastic Optimization | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1231 | Contrastively Disentangled Sequential Variational Autoencoder | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1232 | NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1233 | Linear-Time Probabilistic Solution of Boundary Value Problems | 6.50 | 0.87 | 6, 6, 6, 8 | Poster | Poster | ✔ |

1234 | Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions | 6.50 | 0.87 | 7, 7, 5, 7 | Poster | Poster | |

1235 | Supervising the Transfer of Reasoning Patterns in VQA | 6.50 | 0.87 | 5, 7, 7, 7 | Poster | Poster | |

1236 | Deep Molecular Representation Learning via Fusing Physical and Chemical Information | 6.50 | 1.12 | 5, 6, 8, 7 | Poster | Poster | |

1237 | Distilling Object Detectors with Feature Richness | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1238 | How can classical multidimensional scaling go wrong? | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1239 | Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | ✔ |

1240 | When Are Solutions Connected in Deep Networks? | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1241 | A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1242 | Matching a Desired Causal State via Shift Interventions | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1243 | Ensembling Graph Predictions for AMR Parsing | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1244 | IRM---when it works and when it doesn't: A test case of natural language inference | 6.50 | 1.12 | 5, 8, 7, 6 | Poster | Poster | |

1245 | Morié Attack (MA): A New Potential Risk of Screen Photos | 6.50 | 1.12 | 7, 5, 6, 8 | Poster | Poster | |

1246 | The Limits of Optimal Pricing in the Dark | 6.50 | 1.12 | 6, 8, 7, 5 | Poster | Poster | |

1247 | Joint Modeling of Visual Objects and Relations for Scene Graph Generation | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1248 | Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound | 6.50 | 0.87 | 7, 5, 7, 7 | Poster | Poster | |

1249 | Large-Scale Learning with Fourier Features and Tensor Decompositions | 6.50 | 0.87 | 6, 8, 6, 6 | Poster | Poster | |

1250 | Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | ✔ |

1251 | Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation | 6.50 | 0.50 | 6, 7, 6, 7 | Poster | Poster | |

1252 | Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1253 | To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs | 6.50 | 0.50 | 7, 7, 6, 6 | Poster | Poster | |

1254 | Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II | 6.50 | 0.87 | 6, 6, 6, 8 | Poster | Poster | |

1255 | Motif-based Graph Self-Supervised Learning for Molecular Property Prediction | 6.50 | 1.50 | 7, 4, 8, 7 | Poster | Poster | |

1256 | Sub-Linear Memory: How to Make Performers SLiM | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1257 | Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models | 6.50 | 0.87 | 7, 7, 7, 5 | Poster | Poster | |

1258 | Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1259 | True Few-Shot Learning with Language Models | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1260 | TAAC: Temporally Abstract Actor-Critic for Continuous Control | 6.50 | 0.50 | 7, 6, 6, 7 | Poster | Poster | |

1261 | Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning | 6.50 | 0.50 | 7, 6, 7, 6 | Poster | Poster | |

1262 | Multi-armed Bandit Requiring Monotone Arm Sequences | 6.50 | 0.50 | 6, 6, 7, 7 | Poster | Poster | |

1263 | Minimax Regret for Stochastic Shortest Path | 6.50 | 0.50 | 6, 7, 7, 6 | Poster | Poster | |

1264 | Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications | 6.50 | 0.50 | 7, 6, 6, 7 | Spotlight | Spotlight | |

1265 | Image Generation using Continuous Filter Atoms | 6.50 | 0.50 | 7, 7, 6, 6 | Spotlight | Spotlight | |

1266 | Bootstrapping the Error of Oja's Algorithm | 6.50 | 0.87 | 6, 6, 6, 8 | Spotlight | Spotlight | |

1267 | Learning Generalized Gumbel-max Causal Mechanisms | 6.50 | 0.87 | 5, 7, 7, 7 | Spotlight | Spotlight | ✔ |

1268 | Measuring Generalization with Optimal Transport | 6.50 | 0.87 | 6, 8, 6, 6 | Spotlight | Spotlight | |

1269 | Differentially Private Model Personalization | 6.50 | 0.50 | 6, 7, 6, 7 | Spotlight | Spotlight | |

1270 | Doubly Robust Thompson Sampling with Linear Payoffs | 6.50 | 0.50 | 6, 6, 7, 7 | Spotlight | Spotlight | |

1271 | Online Active Learning with Surrogate Loss Functions | 6.50 | 0.50 | 6, 7, 6, 7 | Spotlight | Spotlight | |

1272 | Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent | 6.50 | 0.50 | 7, 6, 7, 6 | Spotlight | Spotlight | |

1273 | Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems | 6.50 | 1.12 | 7, 8, 5, 6 | Spotlight | Spotlight | |

1274 | RIM: Reliable Influence-based Active Learning on Graphs | 6.50 | 0.50 | 7, 6, 7, 6 | Spotlight | Spotlight | |

1275 | Representation Learning for Event-based Visuomotor Policies | 6.50 | 0.50 | 7, 6, 7, 6 | Spotlight | Spotlight | |

1276 | Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems | 6.50 | 0.50 | 6, 7, 7, 6 | Spotlight | Spotlight | |

1277 | Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent | 6.50 | 2.06 | 7, 3, 8, 8 | Spotlight | Spotlight | |

1278 | Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem | 6.50 | 0.50 | 7, 6, 7, 6 | Spotlight | Spotlight | |

1279 | Variational Inference for Continuous-Time Switching Dynamical Systems | 6.50 | 0.87 | 8, 6, 6, 6 | Spotlight | Poster | ✔ |

1280 | Breaking the Dilemma of Medical Image-to-image Translation | 6.50 | 0.50 | 6, 7, 7, 6 | Spotlight | Spotlight | |

1281 | Coresets for Decision Trees of Signals | 6.50 | 1.50 | 8, 7, 7, 4 | Spotlight | Oral | ✔ |

1282 | Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize | 6.43 | 0.49 | 6, 7, 7, 6, 7, 6, 6 | Poster | Poster | |

1283 | Direct Multi-view Multi-person 3D Pose Estimation | 6.43 | 1.05 | 5, 6, 8, 7, 7, 7, 5 | Poster | Poster | |

1284 | Absolute Neighbour Difference based Correlation Test for Detecting Heteroscedastic Relationships | 6.40 | 0.49 | 6, 6, 7, 6, 7 | Poster | Poster | |

1285 | Robustness of Graph Neural Networks at Scale | 6.40 | 0.49 | 6, 6, 7, 6, 7 | Poster | Poster | |

1286 | Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence | 6.40 | 0.49 | 6, 6, 7, 7, 6 | Poster | Poster | |

1287 | Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck | 6.40 | 0.80 | 6, 8, 6, 6, 6 | Poster | Poster | |

1288 | AutoBalance: Optimized Loss Functions for Imbalanced Data | 6.40 | 1.20 | 7, 4, 7, 7, 7 | Poster | Poster | |

1289 | Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections | 6.40 | 0.80 | 6, 7, 7, 7, 5 | Poster | Poster | |

1290 | End-to-end reconstruction meets data-driven regularization for inverse problems | 6.40 | 0.49 | 6, 7, 6, 7, 6 | Poster | Poster | |

1291 | Dual Parameterization of Sparse Variational Gaussian Processes | 6.40 | 0.80 | 6, 8, 6, 6, 6 | Poster | Poster | |

1292 | Language models enable zero-shot prediction of the effects of mutations on protein function | 6.40 | 1.02 | 8, 7, 6, 5, 6 | Poster | Poster | |

1293 | Support vector machines and linear regression coincide with very high-dimensional features | 6.40 | 0.80 | 7, 5, 6, 7, 7 | Poster | Poster | |

1294 | Learning to Elect | 6.40 | 0.80 | 7, 5, 6, 7, 7 | Poster | Poster | |

1295 | Global-aware Beam Search for Neural Abstractive Summarization | 6.40 | 0.49 | 7, 7, 6, 6, 6 | Poster | Poster | |

1296 | Does Knowledge Distillation Really Work? | 6.40 | 0.80 | 5, 7, 7, 7, 6 | Poster | Poster | ✔ |

1297 | Discovery of Options via Meta-Learned Subgoals | 6.40 | 1.50 | 6, 8, 4, 8, 6 | Poster | Poster | |

1298 | Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models | 6.40 | 0.49 | 7, 6, 6, 6, 7 | Poster | Poster | |

1299 | Improved Regret Bounds for Tracking Experts with Memory | 6.40 | 0.49 | 7, 7, 6, 6, 6 | Poster | Poster | ✔ |

1300 | Individual Privacy Accounting via a Rényi Filter | 6.40 | 0.49 | 7, 6, 7, 6, 6 | Poster | Poster | |

1301 | An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints | 6.40 | 0.80 | 5, 7, 6, 7, 7 | Poster | Poster | |

1302 | Optimality and Stability in Federated Learning: A Game-theoretic Approach | 6.40 | 0.80 | 7, 7, 6, 5, 7 | Poster | Poster | |

1303 | Causal Bandits with Unknown Graph Structure | 6.40 | 1.74 | 7, 7, 3, 8, 7 | Poster | Poster | |

1304 | Robust and Fully-Dynamic Coreset for Continuous-and-Bounded Learning (With Outliers) Problems | 6.40 | 0.49 | 6, 6, 6, 7, 7 | Spotlight | Spotlight | |

1305 | EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback | 6.33 | 0.94 | 7, 7, 5 | Oral | Oral | |

1306 | One More Step Towards Reality: Cooperative Bandits with Imperfect Communication | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | ✔ |

1307 | Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1308 | Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots | 6.33 | 1.25 | 6, 8, 5 | Poster | Reject | ✔ |

1309 | No Regrets for Learning the Prior in Bandits | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1310 | Time-series Generation by Contrastive Imitation | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1311 | Dynamic Normalization and Relay for Video Action Recognition | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1312 | Re-ranking for image retrieval and transductive few-shot classification | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1313 | Can Information Flows Suggest Targets for Interventions in Neural Circuits? | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1314 | Relative Flatness and Generalization | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1315 | Denoising Normalizing Flow | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1316 | Instance-dependent Label-noise Learning under a Structural Causal Model | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1317 | Towards Deeper Deep Reinforcement Learning with Spectral Normalization | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1318 | TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1319 | Modality-Agnostic Topology Aware Localization | 6.33 | 1.70 | 8, 4, 7 | Poster | Poster | |

1320 | Towards Robust and Reliable Algorithmic Recourse | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1321 | Meta-Learning Sparse Implicit Neural Representations | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1322 | On The Structure of Parametric Tournaments with Application to Ranking from Pairwise Comparisons | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1323 | Twins: Revisiting the Design of Spatial Attention in Vision Transformers | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1324 | Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration | 6.33 | 1.25 | 8, 5, 6 | Poster | Poster | |

1325 | Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1326 | 3DP3: 3D Scene Perception via Probabilistic Programming | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1327 | COHESIV: Contrastive Object and Hand Embedding Segmentation In Video | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1328 | EDGE: Explaining Deep Reinforcement Learning Policies | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1329 | Coupled Segmentation and Edge Learning via Dynamic Graph Propagation | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1330 | Towards Enabling Meta-Learning from Target Models | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1331 | Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1332 | Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1333 | Parametrized Quantum Policies for Reinforcement Learning | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1334 | Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1335 | From Canonical Correlation Analysis to Self-supervised Graph Neural Networks | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1336 | Mitigating Forgetting in Online Continual Learning with Neuron Calibration | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1337 | Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration | 6.33 | 1.70 | 7, 4, 8 | Poster | Poster | |

1338 | Differentiable Multiple Shooting Layers | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1339 | Are My Deep Learning Systems Fair? An Empirical Study of Fixed-Seed Training | 6.33 | 0.94 | 7, 7, 5 | Poster | Poster | |

1340 | Topological Detection of Trojaned Neural Networks | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1341 | On the Rate of Convergence of Regularized Learning in Games: From Bandits and Uncertainty to Optimism and Beyond | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1342 | Environment Generation for Zero-Shot Compositional Reinforcement Learning | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1343 | Manipulating SGD with Data Ordering Attacks | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1344 | Leveraging SE(3) Equivariance for Self-supervised Category-Level Object Pose Estimation from Point Clouds | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1345 | Escaping Saddle Points with Compressed SGD | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1346 | Surrogate Regret Bounds for Polyhedral Losses | 6.33 | 1.25 | 6, 5, 8 | Poster | Poster | |

1347 | Indexed Minimum Empirical Divergence for Unimodal Bandits | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1348 | Gone Fishing: Neural Active Learning with Fisher Embeddings | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1349 | Multiclass Boosting and the Cost of Weak Learning | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | ✔ |

1350 | From global to local MDI variable importances for random forests and when they are Shapley values | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1351 | CLIP-It! Language-Guided Video Summarization | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1352 | Directed Spectrum Measures Improve Latent Network Models Of Neural Populations | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1353 | Adaptive Machine Unlearning | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | ✔ |

1354 | Greedy Approximation Algorithms for Active Sequential Hypothesis Testing | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1355 | Posterior Collapse and Latent Variable Non-identifiability | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1356 | Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1357 | Model-Based Domain Generalization | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1358 | (Almost) Free Incentivized Exploration from Decentralized Learning Agents | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1359 | How Fine-Tuning Allows for Effective Meta-Learning | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1360 | Towards robust vision by multi-task learning on monkey visual cortex | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1361 | Multi-task Learning of Order-Consistent Causal Graphs | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1362 | Validation Free and Replication Robust Volume-based Data Valuation | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1363 | Residual Pathway Priors for Soft Equivariance Constraints | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1364 | Identification of the Generalized Condorcet Winner in Multi-dueling Bandits | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1365 | A Gradient Method for Multilevel Optimization | 6.33 | 0.94 | 7, 5, 7 | Poster | Poster | |

1366 | Answering Complex Causal Queries With the Maximum Causal Set Effect | 6.33 | 1.25 | 6, 5, 8 | Poster | Poster | |

1367 | Boost Neural Networks by Checkpoints | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1368 | Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1369 | SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1370 | Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1371 | Particle Cloud Generation with Message Passing Generative Adversarial Networks | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1372 | Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1373 | Bubblewrap: Online tiling and real-time flow prediction on neural manifolds | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1374 | A Highly-Efficient Group Elastic Net Algorithm with an Application to Function-On-Scalar Regression | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1375 | FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1376 | Disentangled Contrastive Learning on Graphs | 6.33 | 1.25 | 8, 6, 5 | Poster | Poster | ✔ |

1377 | Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1378 | A PAC-Bayes Analysis of Adversarial Robustness | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1379 | Efficient Statistical Assessment of Neural Network Corruption Robustness | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | ✔ |

1380 | Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1381 | Unsupervised Representation Transfer for Small Networks: I Believe I Can Distill On-the-Fly | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1382 | DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification | 6.33 | 0.47 | 7, 6, 6, 6, 7, 6 | Poster | Poster | ✔ |

1383 | A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1384 | RoMA: Robust Model Adaptation for Offline Model-based Optimization | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1385 | Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1386 | Dynamic Sasvi: Strong Safe Screening for Norm-Regularized Least Squares | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1387 | Co-evolution Transformer for Protein Contact Prediction | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1388 | Dueling Bandits with Adversarial Sleeping | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1389 | Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1390 | A mechanistic multi-area recurrent network model of decision-making | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1391 | A Note on Sparse Generalized Eigenvalue Problem | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1392 | Spatiotemporal Joint Filter Decomposition in 3D Convolutional Neural Networks | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1393 | Generalized Linear Bandits with Local Differential Privacy | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | ✔ |

1394 | Learning-to-learn non-convex piecewise-Lipschitz functions | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1395 | Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1396 | Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity | 6.33 | 0.94 | 7, 5, 7 | Poster | Poster | ✔ |

1397 | Causal Navigation by Continuous-time Neural Networks | 6.33 | 0.94 | 7, 5, 7 | Poster | Poster | |

1398 | Scalable Intervention Target Estimation in Linear Models | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1399 | Information-constrained optimization: can adaptive processing of gradients help? | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1400 | Gradient-based Hyperparameter Optimization Over Long Horizons | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | ✔ |

1401 | How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1402 | Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | ✔ |

1403 | Dynamic Analysis of Higher-Order Coordination in Neuronal Assemblies via De-Sparsified Orthogonal Matching Pursuit | 6.33 | 0.94 | 7, 5, 7 | Poster | Poster | |

1404 | Active clustering for labeling training data | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | |

1405 | Relative Uncertainty Learning for Facial Expression Recognition | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1406 | Finding Bipartite Components in Hypergraphs | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1407 | Universal Graph Convolutional Networks | 6.33 | 1.25 | 5, 6, 8 | Poster | Poster | |

1408 | Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1409 | A New Theoretical Framework for Fast and Accurate Online Decision-Making | 6.33 | 0.94 | 7, 5, 7 | Poster | Poster | |

1410 | Noise2Score: Tweedie’s Approach to Self-Supervised Image Denoising without Clean Images | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1411 | Improving Conditional Coverage via Orthogonal Quantile Regression | 6.33 | 0.94 | 7, 5, 7 | Poster | Poster | |

1412 | Lattice partition recovery with dyadic CART | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1413 | Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1414 | Recursive Causal Structure Learning in the Presence of Latent Variables and Selection Bias | 6.33 | 0.94 | 5, 7, 7 | Poster | Poster | ✔ |

1415 | Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1416 | Robustness via Uncertainty-aware Cycle Consistency | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1417 | On Large-Cohort Training for Federated Learning | 6.33 | 0.94 | 7, 7, 5 | Poster | Poster | |

1418 | Generating High-Quality Explanations for Navigation in Partially-Revealed Environments | 6.33 | 0.94 | 7, 7, 5 | Poster | Poster | |

1419 | Weak-shot Fine-grained Classification via Similarity Transfer | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | ✔ |

1420 | Personalized Federated Learning With Gaussian Processes | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1421 | NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1422 | Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization | 6.33 | 0.47 | 6, 6, 7 | Poster | Poster | |

1423 | Planning from Pixels in Environments with Combinatorially Hard Search Spaces | 6.33 | 0.47 | 7, 6, 6 | Poster | Poster | |

1424 | Global Convergence of Online Optimization for Nonlinear Model Predictive Control | 6.33 | 0.47 | 6, 7, 6 | Poster | Poster | |

1425 | Offline Reinforcement Learning as One Big Sequence Modeling Problem | 6.33 | 0.94 | 5, 7, 7 | Spotlight | Spotlight | |

1426 | DOCTOR: A Simple Method for Detecting Misclassification Errors | 6.33 | 0.47 | 6, 7, 6 | Spotlight | Spotlight | |

1427 | Clustering Effect of Adversarial Robust Models | 6.33 | 0.47 | 6, 7, 6 | Spotlight | Spotlight | ✔ |

1428 | A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning | 6.33 | 0.47 | 6, 7, 6 | Spotlight | Spotlight | |

1429 | Instance-Conditioned GAN | 6.33 | 0.94 | 7, 7, 5 | Spotlight | Spotlight | |

1430 | Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1431 | Bayesian Optimization of Function Networks | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1432 | Systematic Generalization with Edge Transformers | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1433 | Active Learning of Convex Halfspaces on Graphs | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | ✔ |

1434 | Finite Sample Analysis of Average-Reward TD Learning and
Q
-Learning | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1435 | Asymptotics of the Bootstrap via Stability with Applications to Inference with Model Selection | 6.25 | 1.92 | 3, 8, 7, 7 | Poster | Poster | ✔ |

1436 | On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations | 6.25 | 1.30 | 7, 7, 7, 4 | Poster | Poster | |

1437 | Breaking the centralized barrier for cross-device federated learning | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1438 | HNPE: Leveraging Global Parameters for Neural Posterior Estimation | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1439 | MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1440 | Self-Instantiated Recurrent Units with Dynamic Soft Recursion | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1441 | Learning where to learn: Gradient sparsity in meta and continual learning | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | ✔ |

1442 | Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1443 | Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | ✔ |

1444 | Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | ✔ |

1445 | Continual Learning via Local Module Composition | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1446 | A Trainable Spectral-Spatial Sparse Coding Model for Hyperspectral Image Restoration | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1447 | The balancing principle for parameter choice in distance-regularized domain adaptation | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1448 | Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1449 | Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1450 | Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1451 | Multi-Objective Meta Learning | 6.25 | 1.30 | 5, 8, 5, 7 | Poster | Poster | ✔ |

1452 | Adaptable Agent Populations via a Generative Model of Policies | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1453 | Improving Deep Learning Interpretability by Saliency Guided Training | 6.25 | 1.09 | 5, 6, 6, 8 | Poster | Poster | |

1454 | Interpolation can hurt robust generalization even when there is no noise | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1455 | Open Rule Induction | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1456 | Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks | 6.25 | 1.92 | 7, 3, 8, 7 | Poster | Poster | |

1457 | MAU: A Motion-Aware Unit for Video Prediction and Beyond | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1458 | Towards a Theoretical Framework of Out-of-Distribution Generalization | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | ✔ |

1459 | Time-independent Generalization Bounds for SGLD in Non-convex Settings | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1460 | Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | |

1461 | Medical Dead-ends and Learning to Identify High-Risk States and Treatments | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1462 | Identification and Estimation of Joint Probabilities of Potential Outcomes in Observational Studies with Covariate Information | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1463 | Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1464 | Do Different Tracking Tasks Require Different Appearance Models? | 6.25 | 1.30 | 7, 4, 7, 7 | Poster | Poster | |

1465 | Handling Long-tailed Feature Distribution in AdderNets | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | ✔ |

1466 | Online Control of Unknown Time-Varying Dynamical Systems | 6.25 | 1.92 | 3, 7, 7, 8 | Poster | Poster | |

1467 | Constrained Two-step Look-Ahead Bayesian Optimization | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | ✔ |

1468 | Privately Publishable Per-instance Privacy | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | |

1469 | Pretraining Representations for Data-Efficient Reinforcement Learning | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | |

1470 | Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1471 | Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | ✔ |

1472 | Adversarial Graph Augmentation to Improve Graph Contrastive Learning | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1473 | Word2Fun: Modelling Words as Functions for Diachronic Word Representation | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1474 | Support Recovery of Sparse Signals from a Mixture of Linear Measurements | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Reject | ✔ |

1475 | Scheduling jobs with stochastic holding costs | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1476 | Settling the Variance of Multi-Agent Policy Gradients | 6.25 | 1.30 | 4, 7, 7, 7 | Poster | Poster | |

1477 | Batched Thompson Sampling | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1478 | Testing Probabilistic Circuits | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1479 | Adaptive Online Packing-guided Search for POMDPs | 6.25 | 0.83 | 7, 5, 7, 6 | Poster | Poster | |

1480 | Hypergraph Propagation and Community Selection for Objects Retrieval | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | |

1481 | A universal probabilistic spike count model reveals ongoing modulation of neural variability | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1482 | ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1483 | TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1484 | Credit Assignment Through Broadcasting a Global Error Vector | 6.25 | 1.09 | 6, 8, 6, 5 | Poster | Poster | |

1485 | Training Over-parameterized Models with Non-decomposable Objectives | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1486 | Row-clustering of a Point Process-valued Matrix | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | ✔ |

1487 | Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1488 | Scaling Up Exact Neural Network Compression by ReLU Stability | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1489 | Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1490 | Learning Markov State Abstractions for Deep Reinforcement Learning | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1491 | Lip to Speech Synthesis with Visual Context Attentional GAN | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1492 | Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction | 6.25 | 0.83 | 7, 5, 7, 6 | Poster | Poster | |

1493 | Joint inference and input optimization in equilibrium networks | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1494 | Turing Completeness of Bounded-Precision Recurrent Neural Networks | 6.25 | 2.17 | 3, 6, 9, 7 | Poster | Poster | |

1495 | Average-Reward Learning and Planning with Options | 6.25 | 0.83 | 7, 7, 5, 6 | Poster | Reject | ✔ |

1496 | Scalable Thompson Sampling using Sparse Gaussian Process Models | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | ✔ |

1497 | Dual-stream Network for Visual Recognition | 6.25 | 1.30 | 5, 7, 8, 5 | Poster | Poster | |

1498 | Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected Error | 6.25 | 1.30 | 7, 7, 7, 4 | Poster | Poster | |

1499 | Distributed Deep Learning In Open Collaborations | 6.25 | 1.30 | 7, 8, 5, 5 | Poster | Poster | |

1500 | PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | ✔ |

1501 | On Joint Learning for Solving Placement and Routing in Chip Design | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1502 | Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1503 | Pareto Domain Adaptation | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1504 | Reliable Decisions with Threshold Calibration | 6.25 | 1.79 | 4, 8, 5, 8 | Poster | Poster | ✔ |

1505 | DRONE: Data-aware Low-rank Compression for Large NLP Models | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1506 | GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1507 | Scalars are universal: Equivariant machine learning, structured like classical physics | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | ✔ |

1508 | Residual Relaxation for Multi-view Representation Learning | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1509 | Quantifying and Improving Transferability in Domain Generalization | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1510 | Adversarial Examples in Multi-Layer Random ReLU Networks | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1511 | Weighted model estimation for offline model-based reinforcement learning | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1512 | Which Mutual-Information Representation Learning Objectives are Sufficient for Control? | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | ✔ |

1513 | Predicting What You Already Know Helps: Provable Self-Supervised Learning | 6.25 | 1.48 | 6, 4, 8, 7 | Poster | Poster | |

1514 | Remember What You Want to Forget: Algorithms for Machine Unlearning | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1515 | Score-based Generative Neural Networks for Large-Scale Optimal Transport | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1516 | Continuous-time edge modelling using non-parametric point processes | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1517 | A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1518 | Backdoor Attack with Imperceptible Input and Latent Modification | 6.25 | 1.30 | 7, 7, 7, 4 | Poster | Poster | |

1519 | Double/Debiased Machine Learning for Dynamic Treatment Effects | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1520 | Asynchronous Stochastic Optimization Robust to Arbitrary Delays | 6.25 | 0.83 | 7, 6, 7, 5 | Poster | Poster | |

1521 | Improving Calibration through the Relationship with Adversarial Robustness | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1522 | Towards Biologically Plausible Convolutional Networks | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1523 | Never Go Full Batch (in Stochastic Convex Optimization) | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1524 | Self-Supervised Learning with Kernel Dependence Maximization | 6.25 | 1.09 | 6, 6, 8, 5 | Poster | Poster | |

1525 | Towards Best-of-All-Worlds Online Learning with Feedback Graphs | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1526 | MADE: Exploration via Maximizing Deviation from Explored Regions | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1527 | Automatic Symmetry Discovery with Lie Algebra Convolutional Network | 6.25 | 0.83 | 7, 6, 7, 5 | Poster | Poster | |

1528 | Dirichlet Energy Constrained Learning for Deep Graph Neural Networks | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1529 | Heuristic-Guided Reinforcement Learning | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1530 | Federated Linear Contextual Bandits | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | |

1531 | Antipodes of Label Differential Privacy: PATE and ALIBI | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1532 | Risk-averse Heteroscedastic Bayesian Optimization | 6.25 | 0.83 | 7, 6, 5, 7 | Poster | Poster | |

1533 | Intriguing Properties of Contrastive Losses | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1534 | Label-Imbalanced and Group-Sensitive Classification under Overparameterization | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1535 | Representing Long-Range Context for Graph Neural Networks with Global Attention | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1536 | Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | |

1537 | PolarStream: Streaming Object Detection and Segmentation with Polar Pillars | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1538 | Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation | 6.25 | 0.83 | 7, 7, 5, 6 | Poster | Poster | |

1539 | QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | ✔ |

1540 | Deep Synoptic Monte-Carlo Planning in Reconnaissance Blind Chess | 6.25 | 0.83 | 7, 6, 7, 5 | Poster | Poster | |

1541 | Unifying lower bounds on prediction dimension of convex surrogates | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1542 | Automorphic Equivalence-aware Graph Neural Network | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1543 | Fuzzy Clustering with Similarity Queries | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1544 | Robust Contrastive Learning Using Negative Samples with Diminished Semantics | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1545 | Influence Patterns for Explaining Information Flow in BERT | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | |

1546 | Improving Transferability of Representations via Augmentation-Aware Self-Supervision | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1547 | Does enforcing fairness mitigate biases caused by subpopulation shift? | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1548 | Similarity and Matching of Neural Network Representations | 6.25 | 0.83 | 7, 6, 5, 7 | Poster | Poster | |

1549 | Reusing Combinatorial Structure: Faster Iterative Projections over Submodular Base Polytopes | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | ✔ |

1550 | TokenLearner: Adaptive Space-Time Tokenization for Videos | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1551 | Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces | 6.25 | 0.83 | 7, 5, 7, 6 | Poster | Poster | ✔ |

1552 | You Never Cluster Alone | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1553 | Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1554 | Delayed Gradient Averaging: Tolerate the Communication Latency for Federated Learning | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | |

1555 | Identifying and Benchmarking Natural Out-of-Context Prediction Problems | 6.25 | 1.79 | 8, 8, 5, 4 | Poster | Poster | |

1556 | (Implicit)2
: Implicit Layers for Implicit Representations | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1557 | Curriculum Design for Teaching via Demonstrations: Theory and Applications | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | |

1558 | FedDR – Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimization | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1559 | Adversarial Attacks on Graph Classifiers via Bayesian Optimisation | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1560 | Robust Generalization despite Distribution Shift via Minimum Discriminating Information | 6.25 | 0.83 | 7, 6, 5, 7 | Poster | Poster | |

1561 | A Stochastic Newton Algorithm for Distributed Convex Optimization | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1562 | Scalable and Stable Surrogates for Flexible Classifiers with Fairness Constraints | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1563 | Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1564 | Pooling by Sliced-Wasserstein Embedding | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | ✔ |

1565 | Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity | 6.25 | 1.48 | 4, 6, 7, 8 | Poster | Poster | |

1566 | Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1567 | Structured Denoising Diffusion Models in Discrete State-Spaces | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1568 | Scaling Neural Tangent Kernels via Sketching and Random Features | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1569 | Contrastive Learning of Global and Local Video Representations | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1570 | Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1571 | A Faster Decentralized Algorithm for Nonconvex Minimax Problems | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1572 | Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1573 | A Computationally Efficient Method for Learning Exponential Family Distributions | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | ✔ |

1574 | A Multi-Implicit Neural Representation for Fonts | 6.25 | 1.30 | 7, 7, 7, 4 | Poster | Poster | |

1575 | Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1576 | Parallelizing Thompson Sampling | 6.25 | 1.48 | 7, 6, 4, 8 | Poster | Poster | ✔ |

1577 | Learning Fast-Inference Bayesian Networks | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1578 | Learning 3D Dense Correspondence via Canonical Point Autoencoder | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1579 | Counterfactual Explanations Can Be Manipulated | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1580 | Arbitrary Conditional Distributions with Energy | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | ✔ |

1581 | Agent Modelling under Partial Observability for Deep Reinforcement Learning | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1582 | Towards Robust Bisimulation Metric Learning | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1583 | Faster proximal algorithms for matrix optimization using Jacobi-based eigenvalue methods | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1584 | PiRank: Scalable Learning To Rank via Differentiable Sorting | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1585 | Neural Ensemble Search for Uncertainty Estimation and Dataset Shift | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1586 | Ranking Policy Decisions | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | |

1587 | TopicNet: Semantic Graph-Guided Topic Discovery | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1588 | Assessing Fairness in the Presence of Missing Data | 6.25 | 0.83 | 7, 7, 5, 6 | Poster | Poster | |

1589 | A Framework to Learn with Interpretation | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1590 | AugMax: Adversarial Composition of Random Augmentations for Robust Training | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1591 | Improved Regularization and Robustness for Fine-tuning in Neural Networks | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | ✔ |

1592 | Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1593 | Analyzing the Generalization Capability of SGLD Using Properties of Gaussian Channels | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1594 | Smooth Normalizing Flows | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1595 | Training Neural Networks with Fixed Sparse Masks | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1596 | Learning the optimal Tikhonov regularizer for inverse problems | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1597 | Optimizing Conditional Value-At-Risk of Black-Box Functions | 6.25 | 0.83 | 7, 5, 7, 6 | Poster | Poster | |

1598 | Gradient Inversion with Generative Image Prior | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1599 | Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1600 | High Probability Complexity Bounds for Line Search Based on Stochastic Oracles | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1601 | Square Root Principal Component Pursuit: Tuning-Free Noisy Robust Matrix Recovery | 6.25 | 0.83 | 7, 7, 5, 6 | Poster | Poster | |

1602 | Meta-Learning via Learning with Distributed Memory | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1603 | Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures | 6.25 | 1.48 | 7, 6, 8, 4 | Poster | Poster | |

1604 | Fast Training Method for Stochastic Compositional Optimization Problems | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1605 | Effective Meta-Regularization by Kernelized Proximal Regularization | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1606 | VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1607 | ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1608 | Graph Neural Networks with Local Graph Parameters | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1609 | Differentially Private Sampling from Distributions | 6.25 | 0.83 | 7, 7, 5, 6 | Poster | Poster | |

1610 | When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning? | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1611 | Overcoming the Convex Barrier for Simplex Inputs | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1612 | Probing Inter-modality: Visual Parsing with Self-Attention for Vision-and-Language Pre-training | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1613 | Multi-Facet Clustering Variational Autoencoders | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1614 | Does Knowledge Distillation Really Work? | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | ✔ |

1615 | Tree in Tree: from Decision Trees to Decision Graphs | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1616 | Snowflake: Scaling GNNs to high-dimensional continuous control via parameter freezing | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1617 | Online Convex Optimization with Continuous Switching Constraint | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | |

1618 | Efficient methods for Gaussian Markov random fields under sparse linear constraints | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1619 | Counterfactual Explanations in Sequential Decision Making Under Uncertainty | 6.25 | 1.48 | 6, 8, 4, 7 | Poster | Poster | |

1620 | R-Drop: Regularized Dropout for Neural Networks | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1621 | Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1622 | Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1623 | Do Input Gradients Highlight Discriminative Features? | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1624 | Knowledge-inspired 3D Scene Graph Prediction in Point Cloud | 6.25 | 0.83 | 7, 6, 7, 5 | Poster | Poster | |

1625 | Scalable Bayesian GPFA with automatic relevance determination and discrete noise models | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1626 | Towards Multi-Grained Explainability for Graph Neural Networks | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1627 | Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settings | 6.25 | 1.48 | 6, 8, 4, 7 | Poster | Poster | ✔ |

1628 | Locally Most Powerful Bayesian Test for Out-of-Distribution Detection using Deep Generative Models | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1629 | Neural Circuit Synthesis from Specification Patterns | 6.25 | 1.09 | 6, 8, 5, 6 | Poster | Poster | |

1630 | Directed Graph Contrastive Learning | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1631 | GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1632 | Multi-modal Dependency Tree for Video Captioning | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1633 | Fast Federated Learning in the Presence of Arbitrary Device Unavailability | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1634 | Local Differential Privacy for Regret Minimization in Reinforcement Learning | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1635 | The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | ✔ |

1636 | Recovering Latent Causal Factor for Generalization to Distributional Shifts | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1637 | Distributional Reinforcement Learning for Multi-Dimensional Reward Functions | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1638 | An Information-theoretic Approach to Distribution Shifts | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1639 | Continual World: A Robotic Benchmark For Continual Reinforcement Learning | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1640 | TransformerFusion: Monocular RGB Scene Reconstruction using Transformers | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1641 | Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing | 6.25 | 0.83 | 7, 5, 7, 6 | Poster | Poster | ✔ |

1642 | Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints | 6.25 | 1.30 | 5, 8, 7, 5 | Poster | Poster | |

1643 | Data-Efficient Instance Generation from Instance Discrimination | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1644 | Gradient-based Editing of Memory Examples for Online Task-free Continual Learning | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1645 | Autonomous Reinforcement Learning via Subgoal Curricula | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1646 | Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1647 | Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1648 | NovelD: A Simple yet Effective Exploration Criterion | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1649 | BooVI: Provably Efficient Bootstrapped Value Iteration | 6.25 | 1.09 | 5, 8, 6, 6 | Poster | Poster | |

1650 | A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose | 6.25 | 1.48 | 6, 8, 7, 4 | Poster | Poster | |

1651 | Deformable Butterfly: A Highly Structured and Sparse Linear Transform | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | ✔ |

1652 | Variance-Aware Off-Policy Evaluation with Linear Function Approximation | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1653 | Combinatorial Pure Exploration with Bottleneck Reward Function | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1654 | Compositional Reinforcement Learning from Logical Specifications | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1655 | Hyperparameter Tuning is All You Need for LISTA | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | |

1656 | SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks | 6.25 | 1.09 | 5, 8, 6, 6 | Poster | Poster | |

1657 | PartialFed: Cross-Domain Personalized Federated Learning via Partial Initialization | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1658 | Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1659 | Coarse-to-fine Animal Pose and Shape Estimation | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1660 | Continuous Doubly Constrained Batch Reinforcement Learning | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1661 | Corruption Robust Active Learning | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1662 | Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1663 | Fair Clustering Under a Bounded Cost | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | |

1664 | Learning Distilled Collaboration Graph for Multi-Agent Perception | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | |

1665 | Amortized Variational Inference for Simple Hierarchical Models | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1666 | Online Market Equilibrium with Application to Fair Division | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1667 | Online Multi-Armed Bandits with Adaptive Inference | 6.25 | 1.48 | 6, 8, 4, 7 | Poster | Poster | |

1668 | History Aware Multimodal Transformer for Vision-and-Language Navigation | 6.25 | 1.48 | 6, 8, 7, 4 | Poster | Poster | |

1669 | Deep Extrapolation for Attribute-Enhanced Generation | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | |

1670 | Better Algorithms for Individually Fair
k
-Clustering | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1671 | Learning with Algorithmic Supervision via Continuous Relaxations | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1672 | Preconditioned Gradient Descent for Over-Parameterized Nonconvex Matrix Factorization | 6.25 | 1.09 | 6, 6, 8, 5 | Poster | Poster | |

1673 | How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness? | 6.25 | 0.83 | 7, 6, 5, 7 | Poster | Poster | ✔ |

1674 | Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models | 6.25 | 0.83 | 7, 5, 7, 6 | Poster | Poster | |

1675 | GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | ✔ |

1676 | Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1677 | Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems | 6.25 | 1.09 | 5, 6, 8, 6 | Poster | Poster | |

1678 | Mirror Langevin Monte Carlo: the Case Under Isoperimetry | 6.25 | 0.83 | 7, 6, 5, 7 | Poster | Poster | |

1679 | Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers | 6.25 | 1.09 | 6, 5, 8, 6 | Poster | Poster | |

1680 | Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1681 | Spectral embedding for dynamic networks with stability guarantees | 6.25 | 0.83 | 7, 7, 5, 6 | Poster | Poster | |

1682 | Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1683 | Zero Time Waste: Recycling Predictions in Early Exit Neural Networks | 6.25 | 1.30 | 7, 5, 5, 8 | Poster | Poster | ✔ |

1684 | Differentiable Unsupervised Feature Selection based on a Gated Laplacian | 6.25 | 0.83 | 7, 6, 5, 7 | Poster | Poster | |

1685 | Neural Relightable Participating Media Rendering | 6.25 | 1.30 | 7, 4, 7, 7 | Poster | Poster | |

1686 | Robust and Decomposable Average Precision for Image Retrieval | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1687 | Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1688 | A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | ✔ |

1689 | Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1690 | Infinite Time Horizon Safety of Bayesian Neural Networks | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1691 | DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1692 | Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks | 6.25 | 0.83 | 5, 7, 6, 7 | Poster | Poster | |

1693 | Video Instance Segmentation using Inter-Frame Communication Transformers | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1694 | On the Second-order Convergence Properties of Random Search Methods | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1695 | Contrastive Learning for Neural Topic Model | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | |

1696 | SSMF: Shifting Seasonal Matrix Factorization | 6.25 | 0.83 | 6, 7, 5, 7 | Poster | Poster | ✔ |

1697 | Learning a Single Neuron with Bias Using Gradient Descent | 6.25 | 0.83 | 6, 7, 7, 5 | Poster | Poster | |

1698 | Nonsmooth Implicit Differentiation for Machine-Learning and Optimization | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1699 | Stochastic Anderson Mixing for Nonconvex Stochastic Optimization | 6.25 | 1.30 | 7, 7, 4, 7 | Poster | Poster | ✔ |

1700 | Stochastic Anderson Mixing for Nonconvex Stochastic Optimization | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1701 | CBP: backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | ✔ |

1702 | Unsupervised Motion Representation Learning with Capsule Autoencoders | 6.25 | 0.83 | 7, 7, 6, 5 | Poster | Poster | |

1703 | GemNet: Universal Directional Graph Neural Networks for Molecules | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1704 | Noisy Recurrent Neural Networks | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1705 | Hyperbolic Procrustes Analysis Using Riemannian Geometry | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1706 | Unfolding Taylor's Approximations for Image Restoration | 6.25 | 1.48 | 4, 6, 8, 7 | Poster | Poster | |

1707 | Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System | 6.25 | 1.48 | 4, 8, 7, 6 | Poster | Poster | |

1708 | Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1709 | Scalable Rule-Based Representation Learning for Interpretable Classification | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1710 | Learning to dehaze with polarization | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1711 | MST: Masked Self-Supervised Transformer for Visual Representation | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1712 | Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1713 | ProTo: Program-Guided Transformer for Program-Guided Tasks | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1714 | Chasing Sparsity in Vision Transformers: An End-to-End Exploration | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1715 | Container: Context Aggregation Networks | 6.25 | 0.83 | 5, 6, 7, 7 | Poster | Poster | |

1716 | Online Adaptation to Label Distribution Shift | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | ✔ |

1717 | SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1718 | Hierarchical Skills for Efficient Exploration | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1719 | Understanding Instance-based Interpretability of Variational Auto-Encoders | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1720 | Regularization in ResNet with Stochastic Depth | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1721 | SILG: The Multi-domain Symbolic Interactive Language Grounding Benchmark | 6.25 | 1.30 | 4, 7, 7, 7 | Poster | Reject | ✔ |

1722 | Collaborative Learning in the Jungle (Decentralized, Byzantine, Heterogeneous, Asynchronous and Nonconvex Learning) | 6.25 | 0.83 | 7, 5, 6, 7 | Poster | Poster | |

1723 | Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1724 | Learning interaction rules from multi-animal trajectories via augmented behavioral models | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1725 | Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1726 | Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1727 | Offline Constrained Multi-Objective Reinforcement Learning via Pessimistic Dual Value Iteration | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1728 | LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1729 | Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization | 6.25 | 0.83 | 6, 5, 7, 7 | Poster | Poster | ✔ |

1730 | Efficient and Accurate Gradients for Neural SDEs | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1731 | Robust Allocations with Diversity Constraints | 6.25 | 1.09 | 6, 6, 8, 5 | Poster | Poster | |

1732 | Data Sharing and Compression for Cooperative Networked Control | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1733 | Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models | 6.25 | 0.43 | 7, 6, 6, 6 | Poster | Poster | |

1734 | Who Leads and Who Follows in Strategic Classification? | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1735 | CROCS: Clustering and Retrieval of Cardiac Signals Based on Patient Disease Class, Sex, and Age | 6.25 | 1.30 | 5, 7, 8, 5 | Poster | Poster | |

1736 | Learning Robust Hierarchical Patterns of Human Brain across Many fMRI Studies | 6.25 | 0.43 | 6, 6, 6, 7 | Poster | Poster | |

1737 | Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation | 6.25 | 0.43 | 6, 6, 7, 6 | Poster | Poster | |

1738 | Adjusting for Autocorrelated Errors in Neural Networks for Time Series | 6.25 | 0.83 | 5, 7, 7, 6 | Poster | Poster | |

1739 | Deconvolutional Networks on Graph Data | 6.25 | 0.43 | 6, 7, 6, 6 | Poster | Poster | |

1740 | Fine-Grained Zero-Shot Learning with DNA as Side Information | 6.25 | 0.83 | 7, 6, 7, 5 | Poster | Poster | |

1741 | Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems | 6.25 | 0.43 | 6, 6, 6, 7 | Spotlight | Poster | ✔ |

1742 | Ultrahyperbolic Neural Networks | 6.25 | 0.83 | 7, 7, 6, 5 | Spotlight | Spotlight | |

1743 | Foundations of Symbolic Languages for Model Interpretability | 6.25 | 1.92 | 7, 8, 3, 7 | Spotlight | Spotlight | |

1744 | Program Synthesis Guided Reinforcement Learning for Partially Observed Environments | 6.25 | 1.30 | 7, 7, 4, 7 | Spotlight | Spotlight | ✔ |

1745 | Forster Decomposition and Learning Halfspaces with Noise | 6.25 | 0.43 | 6, 6, 6, 7 | Spotlight | Poster | ✔ |

1746 | Early-stopped neural networks are consistent | 6.25 | 0.43 | 7, 6, 6, 6 | Spotlight | Spotlight | ✔ |

1747 | Node Dependent Local Smoothing for Scalable Graph Learning | 6.25 | 0.43 | 6, 6, 6, 7 | Spotlight | Spotlight | |

1748 | Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer | 6.25 | 0.43 | 6, 6, 7, 6 | Spotlight | Spotlight | |

1749 | Offline RL Without Off-Policy Evaluation | 6.25 | 1.92 | 8, 7, 7, 3 | Spotlight | Poster | ✔ |

1750 | Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer | 6.20 | 0.75 | 6, 6, 5, 7, 7 | Poster | Poster | |

1751 | Stability and Generalization of Bilevel Programming in Hyperparameter Optimization | 6.20 | 0.75 | 5, 7, 6, 7, 6 | Poster | Poster | |

1752 | Explanation-based Data Augmentation for Image Classification | 6.20 | 0.40 | 7, 6, 6, 6, 6 | Poster | Poster | |

1753 | Improved Transformer for High-Resolution GANs | 6.20 | 1.47 | 7, 5, 8, 7, 4 | Poster | Poster | |

1754 | Causal Effect Inference for Structured Treatments | 6.20 | 0.40 | 6, 6, 7, 6, 6 | Poster | Poster | |

1755 | Long-Short Transformer: Efficient Transformers for Language and Vision | 6.20 | 0.40 | 6, 6, 6, 7, 6 | Poster | Poster | |

1756 | The Many Faces of Adversarial Risk | 6.20 | 0.40 | 7, 6, 6, 6, 6 | Poster | Poster | |

1757 | Relaxing Local Robustness | 6.20 | 0.40 | 6, 7, 6, 6, 6 | Poster | Poster | |

1758 | Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM) | 6.20 | 1.33 | 7, 6, 6, 8, 4 | Poster | Poster | |

1759 | Local Explanation of Dialogue Response Generation | 6.20 | 0.40 | 6, 6, 6, 7, 6 | Poster | Poster | |

1760 | The Value of Information When Deciding What to Learn | 6.20 | 0.40 | 6, 6, 7, 6, 6 | Poster | Poster | |

1761 | Provably efficient multi-task reinforcement learning with model transfer | 6.20 | 0.75 | 6, 7, 6, 5, 7 | Poster | Poster | |

1762 | Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families | 6.20 | 0.75 | 7, 7, 6, 6, 5 | Poster | Poster | ✔ |

1763 | Conflict-Averse Gradient Descent for Multi-task learning | 6.20 | 0.75 | 7, 5, 7, 6, 6 | Poster | Poster | |

1764 | Boosted CVaR Classification | 6.20 | 1.17 | 7, 6, 8, 5, 5 | Poster | Poster | |

1765 | Semialgebraic Representation of Monotone Deep Equilibrium Models and Applications to Certification | 6.20 | 0.40 | 6, 7, 6, 6, 6 | Poster | Poster | |

1766 | Replay-Guided Adversarial Environment Design | 6.20 | 0.75 | 5, 6, 6, 7, 7 | Poster | Poster | |

1767 | Towards Lower Bounds on the Depth of ReLU Neural Networks | 6.20 | 0.98 | 5, 5, 7, 7, 7 | Poster | Poster | |

1768 | Error Compensated Distributed SGD Can Be Accelerated | 6.20 | 0.75 | 7, 7, 6, 6, 5 | Poster | Poster | |

1769 | Deconditional Downscaling with Gaussian Processes | 6.20 | 0.75 | 7, 7, 5, 6, 6 | Poster | Poster | |

1770 | Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection | 6.20 | 0.40 | 6, 6, 6, 6, 7 | Poster | Poster | |

1771 | Fast Approximate Dynamic Programming for Infinite-Horizon Markov Decision Processes | 6.20 | 0.75 | 6, 7, 6, 5, 7 | Poster | Poster | |

1772 | LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes | 6.20 | 1.17 | 7, 7, 7, 6, 4 | Poster | Poster | |

1773 | Coresets for Time Series Clustering | 6.20 | 0.75 | 7, 5, 7, 6, 6 | Spotlight | Spotlight | |

1774 | Class-Disentanglement and Applications in Adversarial Detection and Defense | 6.17 | 1.07 | 7, 6, 7, 6, 7, 4 | Poster | Poster | |

1775 | Analysis of Sensing Spectral for Signal Recovery under a Generalized Linear Model | 6.17 | 0.69 | 7, 6, 6, 5, 6, 7 | Poster | Poster | |

1776 | Deep Markov Factor Analysis: Towards Concurrent Temporal and Spatial Analysis of fMRI Data | 6.17 | 0.69 | 7, 7, 6, 6, 6, 5 | Poster | Poster | |

1777 | Causal Identification with Matrix Equations | 6.00 | 0.00 | 6, 6, 6, 6 | Oral | Poster | ✔ |

1778 | Mean-based Best Arm Identification in Stochastic Bandits under Reward Contamination | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1779 | On the Bias-Variance-Cost Tradeoff of Stochastic Optimization | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1780 | Are Transformers more robust than CNNs? | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

1781 | Collapsed Variational Bounds for Bayesian Neural Networks | 6.00 | 1.22 | 8, 6, 5, 5 | Poster | Poster | |

1782 | One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval | 6.00 | 1.87 | 6, 5, 9, 4 | Poster | Poster | |

1783 | CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1784 | Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1785 | Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows | 6.00 | 0.82 | 6, 7, 5 | Poster | Poster | |

1786 | Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots | 6.00 | 1.58 | 5, 8, 4, 7 | Poster | Poster | ✔ |

1787 | Implicit Generative Copulas | 6.00 | 1.22 | 6, 7, 7, 4 | Poster | Poster | |

1788 | Offline Reinforcement Learning with Reverse Model-based Imagination | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

1789 | Dynamic Grained Encoder for Vision Transformers | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

1790 | Activation Sharing with Asymmetric Paths Solves Weight Transport Problem without Bidirectional Connection | 6.00 | 1.22 | 6, 7, 4, 7 | Poster | Poster | |

1791 | Pure Exploration in Kernel and Neural Bandits | 6.00 | 2.35 | 8, 7, 7, 2 | Poster | Poster | |

1792 | Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | ✔ |

1793 | XDO: A Double Oracle Algorithm for Extensive-Form Games | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | ✔ |

1794 | On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | ✔ |

1795 | Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1796 | Online Learning and Control of Complex Dynamical Systems from Sensory Input | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1797 | AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks | 6.00 | 0.82 | 5, 7, 6 | Poster | Poster | |

1798 | Multi-Person 3D Motion Prediction with Multi-Range Transformers | 6.00 | 1.41 | 6, 3, 7, 7, 7, 6 | Poster | Poster | ✔ |

1799 | Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | |

1800 | Test-Time Personalization with a Transformer for Human Pose Estimation | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1801 | Towards Sharper Generalization Bounds for Structured Prediction | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

1802 | SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients | 6.00 | 2.00 | 4, 4, 8, 8 | Poster | Poster | |

1803 | Temporal-attentive Covariance Pooling Networks for Video Recognition | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1804 | Generalized DataWeighting via Class-Level Gradient Manipulation | 6.00 | 1.58 | 4, 7, 8, 5 | Poster | Poster | ✔ |

1805 | Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

1806 | Catastrophic Data Leakage in Vertical Federated Learning | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1807 | DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1808 | TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1809 | DRIVE: One-bit Distributed Mean Estimation | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1810 | Stateful ODE-Nets using Basis Function Expansions | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1811 | Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics | 6.00 | 1.22 | 4, 7, 6, 7 | Poster | Poster | |

1812 | Topic Modeling Revisited: A Document Graph-based Neural Network Perspective | 6.00 | 0.71 | 6, 6, 7, 5 | Poster | Poster | |

1813 | Low-Rank Subspaces in GANs | 6.00 | 1.41 | 7, 4, 7 | Poster | Poster | |

1814 | For high-dimensional hierarchical models, consider exchangeability of effects across covariates instead of across datasets | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1815 | The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization | 6.00 | 1.22 | 5, 8, 6, 5 | Poster | Poster | |

1816 | Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1817 | Unsupervised Learning of Energy Compositions | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1818 | Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess | 6.00 | 1.22 | 7, 6, 4, 7 | Poster | Poster | |

1819 | SWAD: Domain Generalization by Seeking Flat Minima | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1820 | Rectangular Flows for Manifold Learning | 6.00 | 1.10 | 6, 7, 6, 7, 4 | Poster | Poster | |

1821 | Neural Architecture Dilation for Adversarial Robustness | 6.00 | 1.41 | 8, 6, 4, 6 | Poster | Reject | ✔ |

1822 | Neural Architecture Dilation for Adversarial Robustness | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | ✔ |

1823 | Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | ✔ |

1824 | Data Augmentation Can Improve Robustness | 6.00 | 1.00 | 7, 5, 5, 7 | Poster | Poster | |

1825 | Contrastive Laplacian Eigenmaps | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

1826 | Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1827 | SOLQ: Segmenting Objects by Learning Queries | 6.00 | 2.24 | 7, 9, 5, 3 | Poster | Poster | |

1828 | How does a Neural Network's Architecture Impact its Robustness to Noisy Labels? | 6.00 | 1.10 | 6, 5, 6, 8, 5 | Poster | Poster | ✔ |

1829 | Low-Rank Constraints for Fast Inference in Structured Models | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | ✔ |

1830 | Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference | 6.00 | 0.76 | 6, 5, 6, 7, 6, 5, 7 | Poster | Poster | |

1831 | Topological Relational Learning on Graphs | 6.00 | 1.00 | 5, 7, 5, 7 | Poster | Poster | |

1832 | Rectifying the Shortcut Learning of Background for Few-Shot Learning | 6.00 | 1.00 | 5, 7, 7, 5 | Poster | Poster | |

1833 | HRFormer: High-Resolution Vision Transformer for Dense Predict | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

1834 | Learning Causal Semantic Representation for Out-of-Distribution Prediction | 6.00 | 1.00 | 7, 7, 5, 5 | Poster | Poster | |

1835 | Deep Extended Hazard Models for Survival Analysis | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | |

1836 | Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

1837 | VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1838 | Only Train Once: A One-Shot Neural Network Training And Pruning Framework | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

1839 | Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning | 6.00 | 1.22 | 8, 5, 6, 5 | Poster | Poster | |

1840 | Linear and Kernel Classification in the Streaming Model: Improved Bounds for Heavy Hitters | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

1841 | Actively Identifying Causal Effects with Latent Variables Given Only Response Variable Observable | 6.00 | 0.71 | 6, 6, 7, 5 | Poster | Poster | |

1842 | Adversarial Feature Desensitization | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | ✔ |

1843 | Cardinality-Regularized Hawkes-Granger Model | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1844 | Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network | 6.00 | 1.73 | 7, 7, 7, 3 | Poster | Poster | |

1845 | Robustness between the worst and average case | 6.00 | 0.82 | 5, 7, 6 | Poster | Poster | |

1846 | PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1847 | Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | ✔ |

1848 | Open-set Label Noise Can Improve Robustness Against Inherent Label Noise | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | |

1849 | Information-theoretic generalization bounds for black-box learning algorithms | 6.00 | 0.89 | 5, 7, 7, 6, 5 | Poster | Poster | |

1850 | A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis | 6.00 | 1.22 | 6, 7, 7, 4 | Poster | Poster | |

1851 | Least Square Calibration for Peer Reviews | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

1852 | Comprehensive Knowledge Distillation with Causal Intervention | 6.00 | 0.00 | 6, 6, 6, 6, 6 | Poster | Poster | |

1853 | Scallop: From Probabilistic Deductive Databases to Scalable Differentiable Reasoning | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | |

1854 | Adversarial Robustness with Semi-Infinite Constrained Learning | 6.00 | 0.82 | 6, 7, 5 | Poster | Poster | |

1855 | Differentiable Spline Approximations | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1856 | KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1857 | Two-sided fairness in rankings via Lorenz dominance | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1858 | SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | |

1859 | Efficient Active Learning for Gaussian Process Classification by Error Reduction | 6.00 | 1.22 | 6, 5, 5, 8 | Poster | Poster | ✔ |

1860 | Continuous Mean-Covariance Bandits | 6.00 | 1.22 | 6, 4, 7, 7 | Poster | Reject | ✔ |

1861 | A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks | 6.00 | 1.87 | 3, 7, 6, 8 | Poster | Poster | |

1862 | Distributionally Robust Imitation Learning | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | ✔ |

1863 | Parameterized Knowledge Transfer for Personalized Federated Learning | 6.00 | 1.41 | 8, 6, 6, 4 | Poster | Poster | |

1864 | Robust Auction Design in the Auto-bidding World | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

1865 | Parallel and Efficient Hierarchical k-Median Clustering | 6.00 | 1.26 | 7, 4, 7, 5, 7 | Poster | Poster | |

1866 | The Utility of Explainable AI in Ad Hoc Human-Machine Teaming | 6.00 | 1.26 | 7, 8, 5, 5, 5 | Poster | Poster | |

1867 | Adversarial Reweighting for Partial Domain Adaptation | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | ✔ |

1868 | TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive? | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1869 | MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data | 6.00 | 0.82 | 7, 6, 5 | Poster | Poster | |

1870 | Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1871 | Learning Student-Friendly Teacher Networks for Knowledge Distillation | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | ✔ |

1872 | Inverse-Weighted Survival Games | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

1873 | Reinforcement Learning in Reward-Mixing MDPs | 6.00 | 0.89 | 6, 7, 5, 7, 5 | Poster | Poster | |

1874 | SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1875 | Random Noise Defense Against Query-Based Black-Box Attacks | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1876 | Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

1877 | Editing a classifier by rewriting its prediction rules | 6.00 | 1.22 | 7, 4, 6, 7 | Poster | Poster | |

1878 | Nested Counterfactual Identification from Arbitrary Surrogate Experiments | 6.00 | 1.41 | 4, 5, 6, 8, 7 | Poster | Poster | |

1879 | Imitation with Neural Density Models | 6.00 | 1.00 | 7, 7, 5, 5 | Poster | Poster | |

1880 | Neural Pseudo-Label Optimism for the Bank Loan Problem | 6.00 | 1.22 | 4, 7, 6, 7 | Poster | Poster | |

1881 | KS-GNN: Keywords Search over Incomplete Graphs via Graphs Neural Network | 6.00 | 0.82 | 7, 6, 5 | Poster | Poster | |

1882 | SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1883 | Which Mutual-Information Representation Learning Objectives are Sufficient for Control? | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Reject | ✔ |

1884 | Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1885 | Learning Collaborative Policies to Solve NP-hard Routing Problems | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1886 | Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | ✔ |

1887 | CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

1888 | SSAL: Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection | 6.00 | 1.41 | 6, 6, 8, 4 | Poster | Poster | |

1889 | Unsupervised Part Discovery with Contrastive Reconstruction | 6.00 | 0.82 | 5, 7, 6 | Poster | Poster | |

1890 | Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models | 6.00 | 1.41 | 4, 6, 8, 6 | Poster | Poster | |

1891 | Differentiable Synthesis of Program Architectures | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

1892 | Scalable Neural Data Server: A Data Recommender for Transfer Learning | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1893 | Universal Approximation Using Well-Conditioned Normalizing Flows | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | ✔ |

1894 | An analysis of Ermakov-Zolotukhin quadrature using kernels | 6.00 | 1.41 | 6, 6, 4, 8 | Poster | Poster | |

1895 | Bounds all around: training energy-based models with bidirectional bounds | 6.00 | 1.22 | 5, 8, 5, 6 | Poster | Poster | |

1896 | Recurrent Bayesian Classifier Chains for Exact Multi-Label Classification | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1897 | Robust Visual Reasoning via Language Guided Neural Module Networks | 6.00 | 1.00 | 7, 5, 7, 5 | Poster | Poster | |

1898 | Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | ✔ |

1899 | Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis | 6.00 | 1.41 | 6, 6, 4, 8 | Poster | Poster | ✔ |

1900 | Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | |

1901 | Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction | 6.00 | 0.82 | 5, 7, 6 | Poster | Poster | |

1902 | Relational Self-Attention: What's Missing in Attention for Video Understanding | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Reject | ✔ |

1903 | A Bayesian-Symbolic Approach to Reasoning and Learning in Intuitive Physics | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1904 | Fairness via Representation Neutralization | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Reject | ✔ |

1905 | Hierarchical Reinforcement Learning with Timed Subgoals | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1906 | On Model Calibration for Long-Tailed Object Detection and Instance Segmentation | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1907 | Representation Costs of Linear Neural Networks: Analysis and Design | 6.00 | 0.00 | 6, 6, 6 | Poster | Reject | ✔ |

1908 | NTopo: Mesh-free Topology Optimization using Implicit Neural Representations | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1909 | Monte Carlo Tree Search With Iteratively Refining State Abstractions | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1910 | Soft Calibration Objectives for Neural Networks | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1911 | Rate-Optimal Subspace Estimation on Random Graphs | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1912 | PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1913 | Decentralized Q-learning in Zero-sum Markov Games | 6.00 | 1.26 | 5, 5, 7, 8, 5 | Poster | Poster | |

1914 | Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings | 6.00 | 1.22 | 7, 6, 7, 4 | Poster | Poster | |

1915 | Functional Neural Networks for Parametric Image Restoration Problems | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1916 | How Does it Sound? | 6.00 | 1.10 | 7, 6, 7, 4, 6 | Poster | Poster | |

1917 | Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization | 6.00 | 1.73 | 3, 7, 7, 7 | Poster | Poster | |

1918 | On Success and Simplicity: A Second Look at Transferable Targeted Attacks | 6.00 | 1.22 | 7, 6, 4, 7 | Poster | Reject | ✔ |

1919 | CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

1920 | Distributed Saddle-Point Problems Under Data Similarity | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | ✔ |

1921 | K-level Reasoning for Zero-Shot Coordination in Hanabi | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | |

1922 | Knowledge-Adaptation Priors | 6.00 | 1.22 | 7, 4, 7, 6 | Poster | Poster | |

1923 | How Modular should Neural Module Networks Be for Systematic Generalization? | 6.00 | 1.22 | 6, 4, 7, 7 | Poster | Poster | |

1924 | Piper: Multidimensional Planner for DNN Parallelization | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1925 | Autobahn: Automorphism-based Graph Neural Nets | 6.00 | 0.82 | 6, 7, 5 | Poster | Poster | |

1926 | QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning | 6.00 | 1.00 | 5, 7, 5, 7 | Poster | Poster | ✔ |

1927 | Inverse Problems Leveraging Pre-trained Contrastive Representations | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1928 | Learning to Schedule Heuristics in Branch and Bound | 6.00 | 1.22 | 4, 7, 6, 7 | Poster | Poster | ✔ |

1929 | Generative vs. Discriminative: Rethinking The Meta-Continual Learning | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

1930 | Variational Multi-Task Learning with Gumbel-Softmax Priors | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | |

1931 | Meta-learning with an Adaptive Task Scheduler | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

1932 | Streaming Belief Propagation for Community Detection | 6.00 | 1.22 | 5, 5, 6, 8 | Poster | Reject | ✔ |

1933 | Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks | 6.00 | 2.35 | 8, 7, 7, 2 | Poster | Poster | |

1934 | On learning sparse vectors from mixture of responses | 6.00 | 1.41 | 8, 7, 5, 6, 4 | Poster | Poster | ✔ |

1935 | Object DGCNN: 3D Object Detection using Dynamic Graphs | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1936 | Deep Learning Through the Lens of Example Difficulty | 6.00 | 1.22 | 6, 8, 5, 5 | Poster | Reject | ✔ |

1937 | Deep Learning Through the Lens of Example Difficulty | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | ✔ |

1938 | Learning Transferable Adversarial Perturbations | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1939 | Iterative Teacher-Aware Learning | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1940 | Reinforcement Learning based Disease Progression Model for Alzheimer’s Disease | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

1941 | Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1942 | Alignment Attention by Matching Key and Query Distributions | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | |

1943 | Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory | 6.00 | 0.71 | 6, 6, 7, 5 | Poster | Poster | |

1944 | Revisiting 3D Object Detection From an Egocentric Perspective | 6.00 | 1.41 | 6, 6, 4, 8 | Poster | Poster | |

1945 | Accurate Point Cloud Registration with Robust Optimal Transport | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

1946 | Topological Attention for Time Series Forecasting | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1947 | Learning to Learn Dense Gaussian Processes for Few-Shot Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1948 | Variational Model Inversion Attacks | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1949 | Improving Compositionality of Neural Networks by Decoding Representations to Inputs | 6.00 | 1.58 | 8, 7, 4, 5 | Poster | Poster | ✔ |

1950 | Kernel Identification Through Transformers | 6.00 | 0.82 | 5, 7, 6 | Poster | Poster | |

1951 | On the Power of Edge Independent Graph Models | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

1952 | Communication-efficient SGD: From Local SGD to One-Shot Averaging | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

1953 | Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | ✔ |

1954 | Efficient Bayesian network structure learning via local Markov boundary search | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | ✔ |

1955 | Temporally Abstract Partial Models | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1956 | Wisdom of the Crowd Voting: Truthful Aggregation of Voter Information and Preferences | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

1957 | S
3
: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks | 6.00 | 2.45 | 8, 6, 8, 2 | Poster | Poster | |

1958 | Distributed Principal Component Analysis with Limited Communication | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1959 | Structural Credit Assignment in Neural Networks using Reinforcement Learning | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | |

1960 | How Fine-Tuning Allows for Effective Meta-Learning | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | ✔ |

1961 | Targeted Neural Dynamical Modeling | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | |

1962 | Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution | 6.00 | 1.22 | 6, 8, 5, 5 | Poster | Poster | ✔ |

1963 | VAST: Value Function Factorization with Variable Agent Sub-Teams | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | |

1964 | A Computationally Efficient Method for Learning Exponential Family Distributions | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | ✔ |

1965 | Set Prediction in the Latent Space | 6.00 | 0.63 | 6, 6, 7, 5, 6 | Poster | Poster | |

1966 | Dynamic COVID risk assessment accounting for community virus exposure from a spatial-temporal transmission model | 6.00 | 0.82 | 6, 5, 7 | Poster | Poster | |

1967 | Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

1968 | Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces | 6.00 | 0.71 | 6, 7, 5, 6 | Poster | Poster | ✔ |

1969 | Arbitrary Conditional Distributions with Energy | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Reject | ✔ |

1970 | ELLA: Exploration through Learned Language Abstraction | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1971 | Looking Beyond Single Images for Contrastive Semantic Segmentation Learning | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1972 | Tracking Without Re-recognition in Humans and Machines | 6.00 | 2.16 | 3, 8, 7 | Poster | Poster | |

1973 | Discovering and Achieving Goals via World Models | 6.00 | 0.00 | 6, 6, 6, 6, 6 | Poster | Poster | |

1974 | Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1975 | Pipeline Combinators for Gradual AutoML | 6.00 | 1.22 | 4, 7, 6, 7 | Poster | Poster | ✔ |

1976 | Unifying Width-Reduced Methods for Quasi-Self-Concordant Optimization | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1977 | Exploiting a Zoo of Checkpoints for Unseen Tasks | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1978 | Encoding Spatial Distribution of Convolutional Features for Texture Representation | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1979 | Gradient Driven Rewards to Guarantee Fairness in Collaborative Machine Learning | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

1980 | Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking | 6.00 | 0.71 | 6, 7, 6, 5 | Poster | Poster | |

1981 | Post-Contextual-Bandit Inference | 6.00 | 1.73 | 7, 7, 7, 3 | Poster | Poster | |

1982 | Solving Soft Clustering Ensemble via
k
-Sparse Discrete Wasserstein Barycenter | 6.00 | 0.71 | 6, 6, 7, 5 | Poster | Poster | |

1983 | Model-Based Reinforcement Learning via Imagination with Derived Memory | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1984 | Adaptive Sampling for Minimax Fair Classification | 6.00 | 1.41 | 4, 6, 6, 8 | Poster | Poster | |

1985 | BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1986 | Understanding Bandits with Graph Feedback | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | ✔ |

1987 | Searching the Search Space of Vision Transformer | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

1988 | Collaborative Causal Discovery with Atomic Interventions | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1989 | DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

1990 | Intermediate Layers Matter in Momentum Contrastive Self Supervised Learning | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1991 | Referring Transformer: A One-step Approach to Multi-task Visual Grounding | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

1992 | Unbalanced Optimal Transport through Non-negative Penalized Linear Regression | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

1993 | Diverse Message Passing for Attribute with Heterophily | 6.00 | 1.22 | 7, 6, 4, 7 | Poster | Poster | |

1994 | When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

1995 | Federated Multi-Task Learning under a Mixture of Distributions | 6.00 | 1.22 | 6, 7, 7, 4 | Poster | Poster | |

1996 | Explaining Hyperparameter Optimization via Partial Dependence Plots | 6.00 | 0.82 | 7, 6, 5 | Poster | Poster | |

1997 | Exploiting Opponents Under Utility Constraints in Sequential Games | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

1998 | Memory-Efficient Approximation Algorithms for Max-k-Cut and Correlation Clustering | 6.00 | 1.22 | 7, 7, 6, 4 | Poster | Poster | |

1999 | Consistent Non-Parametric Methods for Maximizing Robustness | 6.00 | 1.00 | 5, 7, 5, 7 | Poster | Poster | |

2000 | Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models | 6.00 | 1.00 | 7, 5, 5, 7 | Poster | Poster | |

2001 | Towards Tight Communication Lower Bounds for Distributed Optimisation | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2002 | Fast Algorithms for
L∞
-constrained S-rectangular Robust MDPs | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | ✔ |

2003 | Directed Probabilistic Watershed | 6.00 | 1.10 | 6, 6, 4, 7, 7 | Poster | Poster | |

2004 | Distribution-free inference for regression: discrete, continuous, and in between | 6.00 | 1.58 | 8, 4, 7, 5 | Poster | Reject | ✔ |

2005 | Think Big, Teach Small: Do Language Models Distil Occam’s Razor? | 6.00 | 0.00 | 6, 6, 6, 6, 6 | Poster | Poster | |

2006 | Fair Algorithms for Multi-Agent Multi-Armed Bandits | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

2007 | ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2008 | A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | ✔ |

2009 | Local policy search with Bayesian optimization | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

2010 | It Has Potential: Gradient-Driven Denoisers for Convergent Solutions to Inverse Problems | 6.00 | 0.89 | 5, 6, 7, 5, 7 | Poster | Poster | |

2011 | EIGNN: Efficient Infinite-Depth Graph Neural Networks | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | |

2012 | Regret Minimization Experience Replay in Off-Policy Reinforcement Learning | 6.00 | 1.87 | 6, 5, 4, 9 | Poster | Reject | ✔ |

2013 | Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2014 | A Theoretical Analysis of Fine-tuning with Linear Teachers | 6.00 | 1.22 | 6, 7, 4, 7 | Poster | Poster | |

2015 | Grounding inductive biases in natural images: invariance stems from variations in data | 6.00 | 1.58 | 8, 5, 4, 7 | Poster | Poster | |

2016 | Adaptive Proximal Gradient Methods for Structured Neural Networks | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

2017 | Metropolis-Hastings Data Augmentation for Graph Neural Networks | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2018 | Landmark-RxR: Solving Vision-and-Language Navigation with Fine-Grained Alignment Supervision | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

2019 | DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2020 | Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD | 6.00 | 0.63 | 7, 6, 6, 6, 5 | Poster | Poster | |

2021 | Memory Efficient Meta-Learning with Large Images | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2022 | Stochastic Bias-Reduced Gradient Methods | 6.00 | 1.22 | 7, 7, 4, 6 | Poster | Poster | |

2023 | Large-Scale Unsupervised Object Discovery | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

2024 | LSH-SMILE: Locality Sensitive Hashing Accelerated Simulation and Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2025 | Stateful Strategic Regression | 6.00 | 1.22 | 5, 6, 5, 8 | Poster | Poster | |

2026 | No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | |

2027 | Disentangled Contrastive Learning on Graphs | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | ✔ |

2028 | Last iterate convergence of SGD for Least-Squares in the Interpolation regime. | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2029 | Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning | 6.00 | 0.82 | 6, 5, 7 | Poster | Poster | ✔ |

2030 | Dual Progressive Prototype Network for Generalized Zero-Shot Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2031 | An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias | 6.00 | 1.41 | 4, 8, 6, 6 | Poster | Poster | |

2032 | OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization | 6.00 | 0.63 | 6, 7, 6, 6, 5 | Poster | Poster | |

2033 | Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

2034 | Fast Abductive Learning by Similarity-based Consistency Optimization | 6.00 | 1.22 | 7, 7, 6, 4 | Poster | Poster | |

2035 | Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

2036 | Faster Non-asymptotic Convergence for Double Q-learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2037 | DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification | 6.00 | 0.71 | 6, 7, 5, 6 | Poster | Poster | ✔ |

2038 | CATs: Cost Aggregation Transformers for Visual Correspondence | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

2039 | Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection | 6.00 | 1.00 | 7, 5, 7, 5 | Poster | Poster | ✔ |

2040 | Locally differentially private estimation of functionals of discrete distributions | 6.00 | 0.71 | 6, 6, 7, 5 | Poster | Poster | ✔ |

2041 | Solving Graph-based Public Goods Games with Tree Search and Imitation Learning | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2042 | DeepReduce: A Sparse-tensor Communication Framework for Federated Deep Learning | 6.00 | 1.00 | 5, 7, 5, 7 | Poster | Poster | |

2043 | Misspecified Gaussian Process Bandit Optimization | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | |

2044 | Conformal Time-series Forecasting | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2045 | 3D Pose Transfer with Correspondence Learning and Mesh Refinement | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2046 | Regularized Softmax Deep Multi-Agent Q-Learning | 6.00 | 1.41 | 7, 4, 7 | Poster | Poster | |

2047 | Edge Representation Learning with Hypergraphs | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | ✔ |

2048 | Parameter-free HE-friendly Logistic Regression | 6.00 | 0.71 | 6, 7, 5, 6 | Poster | Poster | |

2049 | Not All Low-Pass Filters are Robust in Graph Convolutional Networks | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2050 | Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective | 6.00 | 1.22 | 7, 6, 4, 7 | Poster | Poster | |

2051 | Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration | 6.00 | 0.71 | 6, 5, 6, 7 | Poster | Poster | |

2052 | Entropy-based adaptive Hamiltonian Monte Carlo | 6.00 | 0.82 | 6, 7, 5 | Poster | Poster | |

2053 | Optimal Algorithms for Stochastic Contextual Preference Bandits | 6.00 | 0.82 | 7, 6, 5 | Poster | Poster | |

2054 | Neighborhood Reconstructing Autoencoders | 6.00 | 1.87 | 7, 3, 8, 6 | Poster | Poster | |

2055 | Non-Gaussian Gaussian Processes for Few-Shot Regression | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

2056 | CHIP: CHannel Independence-based Pruning for Compact Neural Networks | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

2057 | FACMAC: Factored Multi-Agent Centralised Policy Gradients | 6.00 | 1.10 | 7, 4, 7, 6, 6 | Poster | Poster | ✔ |

2058 | Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach | 6.00 | 1.22 | 6, 4, 7, 7 | Poster | Poster | |

2059 | BNS: Building Network Structures Dynamically for Continual Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2060 | RelaySum for Decentralized Deep Learning on Heterogeneous Data | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2061 | Learning curves of generic features maps for realistic datasets with a teacher-student model | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2062 | Sample Selection for Fair and Robust Training | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2063 | Learning Domain Invariant Representations in Goal-conditioned Block MDPs | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2064 | Generalization Guarantee of SGD for Pairwise Learning | 6.00 | 0.82 | 7, 6, 5 | Poster | Poster | |

2065 | Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation | 6.00 | 1.00 | 5, 5, 7, 7 | Poster | Poster | |

2066 | Implicit Task-Driven Probability Discrepancy Measure for Unsupervised Domain Adaptation | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2067 | What Makes Multi-Modal Learning Better than Single (Provably) | 6.00 | 1.22 | 6, 4, 7, 7 | Poster | Poster | |

2068 | CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings | 6.00 | 1.41 | 8, 6, 6, 4 | Poster | Poster | |

2069 | Adapting to function difficulty and growth conditions in private optimization | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

2070 | Counterfactual Maximum Likelihood Estimation for Training Deep Networks | 6.00 | 1.10 | 4, 6, 6, 7, 7 | Poster | Poster | |

2071 | Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2072 | Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness | 6.00 | 1.22 | 7, 4, 6, 7 | Poster | Poster | |

2073 | Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning | 6.00 | 0.89 | 5, 6, 7, 7, 5 | Poster | Reject | ✔ |

2074 | Towards Context-Agnostic Learning Using Synthetic Data | 6.00 | 0.82 | 6, 5, 7 | Poster | Poster | |

2075 | Reinforcement Learning with Latent Flow | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

2076 | Approximate optimization of convex functions with outlier noise | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2077 | Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2078 | Label Noise SGD Provably Prefers Flat Global Minimizers | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

2079 | Learning to Assimilate in Chaotic Dynamical Systems | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2080 | Uncertainty Quantification and Deep Ensembles | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2081 | Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

2082 | Topology-Imbalance Learning for Semi-Supervised Node Classification | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | ✔ |

2083 | Confident Anchor-Induced Multi-Source Free Domain Adaptation | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

2084 | CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2085 | Recognizing Vector Graphics without Rasterization | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2086 | Scalable Diverse Model Selection for Accessible Transfer Learning | 6.00 | 1.26 | 5, 8, 5, 7, 5 | Poster | Poster | |

2087 | Increasing Liquid State Machine Performance with Edge-of-Chaos Dynamics Organized by Astrocyte-modulated Plasticity | 6.00 | 1.22 | 4, 6, 7, 7 | Poster | Reject | ✔ |

2088 | Fast Projection onto the Capped Simplex with Applications to Sparse Regression in Bioinformatics | 6.00 | 1.22 | 7, 4, 7, 6 | Poster | Poster | |

2089 | Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

2090 | The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

2091 | Bandits with Knapsacks beyond the Worst Case | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2092 | Offline Meta Reinforcement Learning -- Identifiability Challenges and Effective Data Collection Strategies | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | |

2093 | Scaling Gaussian Processes with Derivative Information Using Variational Inference | 6.00 | 1.00 | 7, 5, 5, 7 | Poster | Poster | |

2094 | Gradient-based Hyperparameter Optimization Over Long Horizons | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2095 | A Surrogate Objective Framework for Prediction+Programming with Soft Constraints | 6.00 | 1.22 | 6, 7, 7, 4 | Poster | Poster | |

2096 | A Convergence Analysis of Gradient Descent on Graph Neural Networks | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2097 | Exact Privacy Guarantees for Markov Chain Implementations of the Exponential Mechanism with Artificial Atoms | 6.00 | 0.63 | 6, 6, 7, 5, 6 | Poster | Poster | |

2098 | Slow Learning and Fast Inference: Efficient Graph Similarity Computation via Knowledge Distillation | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2099 | On the Algorithmic Stability of Adversarial Training | 6.00 | 1.00 | 7, 7, 5, 5 | Poster | Poster | |

2100 | Learning Riemannian metric for disease progression modeling | 6.00 | 1.00 | 5, 7, 7, 5 | Poster | Reject | ✔ |

2101 | BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer | 6.00 | 1.10 | 6, 7, 7, 4, 6 | Poster | Poster | |

2102 | Provably Strict Generalisation Benefit for Invariance in Kernel Methods | 6.00 | 1.22 | 8, 5, 5, 6 | Poster | Poster | ✔ |

2103 | SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2104 | Change Point Detection via Multivariate Singular Spectrum Analysis | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2105 | Efficient constrained sampling via the mirror-Langevin algorithm | 6.00 | 0.71 | 5, 7, 6, 6 | Poster | Poster | |

2106 | The Lazy Online Subgradient Algorithm is Universal on Strongly Convex Domains | 6.00 | 1.41 | 4, 6, 8, 6 | Poster | Poster | |

2107 | Distributed Machine Learning with Sparse Heterogeneous Data | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2108 | Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | |

2109 | Multilingual Pre-training with Universal Dependency Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2110 | Differentiable Spike: Rethinking Gradient-Descent for Training Spiking Neural Networks | 6.00 | 1.22 | 8, 5, 6, 5 | Poster | Poster | |

2111 | Going Beyond Linear Transformers with Recurrent Fast Weight Programmers | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

2112 | BayesIMP: Uncertainty Quantification for Causal Data Fusion | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2113 | Beyond Bandit Feedback in Online Multiclass Classification | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Reject | ✔ |

2114 | Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2115 | SketchGen: Generating Constrained CAD Sketches | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

2116 | Photonic Differential Privacy with Direct Feedback Alignment | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | |

2117 | TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2118 | Curriculum Learning for Vision-and-Language Navigation | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | |

2119 | Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2120 | Adversarial Regression with Doubly Non-negative Weighting Matrices | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Reject | ✔ |

2121 | Sparse Uncertainty Representation in Deep Learning with Inducing Weights | 6.00 | 1.22 | 7, 7, 4, 6 | Poster | Poster | |

2122 | MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction | 6.00 | 0.71 | 6, 6, 5, 7 | Poster | Poster | |

2123 | Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2124 | Anti-Backdoor Learning: Training Clean Models on Poisoned Data | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Poster | |

2125 | Sample Complexity Bounds for Active Ranking from Multi-wise Comparisons | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

2126 | Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2127 | Self-Interpretable Model with Transformation Equivariant Interpretation | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2128 | Robust Counterfactual Explanations on Graph Neural Networks | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | ✔ |

2129 | FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling | 6.00 | 1.73 | 7, 3, 7, 7 | Poster | Poster | |

2130 | Algorithmic stability and generalization of an unsupervised feature selection algorithm | 6.00 | 0.82 | 5, 7, 6 | Poster | Poster | |

2131 | Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration | 6.00 | 1.00 | 5, 5, 7, 7 | Poster | Poster | |

2132 | Differentially Private Multi-Armed Bandits in the Shuffle Model | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | ✔ |

2133 | SyncTwin: Treatment Effect Estimation with Longitudinal Outcomes | 6.00 | 1.22 | 6, 5, 5, 8 | Poster | Poster | |

2134 | Hyperbolic Procrustes Analysis Using Riemannian Geometry | 6.00 | 0.71 | 7, 6, 6, 5 | Poster | Poster | ✔ |

2135 | Exploiting Domain-Specific Features to Enhance Domain Generalization | 6.00 | 1.22 | 4, 7, 7, 6 | Poster | Poster | ✔ |

2136 | ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2137 | Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations | 6.00 | 1.00 | 7, 5, 7, 5 | Poster | Poster | |

2138 | Non-asymptotic Error Bounds for Bidirectional GANs | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2139 | Faster Neural Network Training with Approximate Tensor Operations | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2140 | A Max-Min Entropy Framework for Reinforcement Learning | 6.00 | 1.22 | 7, 4, 6, 7 | Poster | Poster | |

2141 | Fast Tucker Rank Reduction for Non-Negative Tensors Using Mean-Field Approximation | 6.00 | 1.22 | 7, 7, 4, 6 | Poster | Poster | |

2142 | Lattice partition recovery with dyadic CART | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | ✔ |

2143 | ReAct: Out-of-distribution Detection With Rectified Activations | 6.00 | 1.22 | 7, 6, 4, 7 | Poster | Poster | |

2144 | CCVS: Context-aware Controllable Video Synthesis | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | |

2145 | Sparse Spiking Gradient Descent | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

2146 | Revisiting Smoothed Online Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2147 | Online Adaptation to Label Distribution Shift | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | ✔ |

2148 | Meta-Learning for Relative Density-Ratio Estimation | 6.00 | 1.22 | 7, 4, 7, 6 | Poster | Poster | |

2149 | Posterior Meta-Replay for Continual Learning | 6.00 | 1.73 | 7, 7, 7, 3 | Poster | Poster | |

2150 | Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks | 6.00 | 0.82 | 5, 6, 7 | Poster | Poster | |

2151 | Multi-view Contrastive Graph Clustering | 6.00 | 0.63 | 6, 7, 6, 6, 5 | Poster | Poster | |

2152 | Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark | 6.00 | 0.82 | 6, 7, 5 | Poster | Poster | |

2153 | Learning Knowledge Graph-based World Models of Textual Environments | 6.00 | 1.22 | 6, 4, 7, 7 | Poster | Poster | |

2154 | USCO-Solver: Solving Undetermined Stochastic Combinatorial Optimization Problems | 6.00 | 0.71 | 5, 6, 7, 6 | Poster | Poster | |

2155 | Instance-optimal Mean Estimation Under Differential Privacy | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2156 | Accurately Solving Rod Dynamics with Graph Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2157 | AFEC: Active Forgetting of Negative Transfer in Continual Learning | 6.00 | 0.00 | 6, 6, 6, 6 | Poster | Poster | |

2158 | Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory | 6.00 | 0.82 | 6, 5, 7 | Poster | Poster | |

2159 | Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling | 6.00 | 0.71 | 6, 5, 7, 6 | Poster | Reject | ✔ |

2160 | Label Disentanglement in Partition-based Extreme Multilabel Classification | 6.00 | 1.22 | 7, 4, 7, 6 | Poster | Poster | |

2161 | Locally private online change point detection | 6.00 | 0.00 | 6, 6, 6 | Poster | Poster | ✔ |

2162 | One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective | 6.00 | 1.41 | 4, 7, 7 | Poster | Poster | |

2163 | PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | |

2164 | Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model | 6.00 | 0.71 | 5, 6, 6, 7 | Poster | Poster | |

2165 | Stochastic
L♮
-convex Function Minimization | 6.00 | 0.71 | 7, 6, 5, 6 | Poster | Poster | |

2166 | A Prototype-Oriented Framework for Unsupervised Domain Adaptation | 6.00 | 1.22 | 7, 7, 6, 4 | Poster | Poster | |

2167 | Training Neural Networks is ER-complete | 6.00 | 1.87 | 9, 5, 6, 4 | Poster | Poster | |

2168 | Interpretable agent communication from scratch (with a generic visual processor emerging on the side) | 6.00 | 1.41 | 5, 8, 5 | Poster | Poster | |

2169 | Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation | 6.00 | 1.22 | 7, 6, 4, 7 | Poster | Poster | ✔ |

2170 | Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer | 6.00 | 0.71 | 7, 5, 6, 6 | Poster | Poster | ✔ |

2171 | Neural Distance Embeddings for Biological Sequences | 6.00 | 1.22 | 4, 6, 7, 7 | Poster | Poster | |

2172 | On the interplay between data structure and loss function in classification problems | 6.00 | 0.82 | 7, 5, 6 | Poster | Poster | |

2173 | RED : Looking for Redundancies for Data-FreeStructured Compression of Deep Neural Networks | 6.00 | 0.82 | 6, 7, 5 | Poster | Poster | |

2174 | Focal Attention for Long-Range Interactions in Vision Transformers | 6.00 | 0.00 | 6, 6, 6, 6 | Spotlight | Spotlight | |

2175 | Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization | 6.00 | 0.71 | 7, 6, 6, 5 | Spotlight | Spotlight | |

2176 | Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate | 6.00 | 1.87 | 6, 3, 7, 8 | Spotlight | Spotlight | |

2177 | Sequential Algorithms for Testing Closeness of Distributions | 6.00 | 0.00 | 6, 6, 6 | Spotlight | Spotlight | |

2178 | Collaborating with Humans without Human Data | 6.00 | 1.41 | 5, 8, 5 | Spotlight | Reject | ✔ |

2179 | Clustering Effect of Adversarial Robust Models | 6.00 | 0.82 | 6, 7, 5 | Spotlight | Poster | ✔ |

2180 | Sliced Mutual Information: A Scalable Measure of Statistical Dependence | 6.00 | 1.22 | 7, 6, 7, 4 | Spotlight | Poster | ✔ |

2181 | 3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds | 5.86 | 0.83 | 6, 7, 4, 6, 6, 6, 6 | Poster | Poster | |

2182 | Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds | 5.83 | 0.69 | 7, 6, 5, 5, 6, 6 | Poster | Poster | |

2183 | argmax centroid | 5.83 | 0.69 | 6, 6, 5, 5, 6, 7 | Poster | Poster | |

2184 | Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks | 5.83 | 0.90 | 6, 6, 6, 7, 6, 4 | Poster | Poster | |

2185 | When Expressivity Meets Trainability: Fewer than
n
Neurons Can Work | 5.80 | 0.40 | 5, 6, 6, 6, 6 | Poster | Reject | ✔ |

2186 | A Unified View of cGANs with and without Classifiers | 5.80 | 0.40 | 6, 6, 5, 6, 6 | Poster | Poster | |

2187 | Scalars are universal: Equivariant machine learning, structured like classical physics | 5.80 | 0.98 | 4, 6, 7, 6, 6 | Poster | Poster | ✔ |

2188 | Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation | 5.80 | 0.98 | 6, 6, 7, 6, 4 | Poster | Poster | |

2189 | Stronger NAS with Weaker Predictors | 5.80 | 0.98 | 4, 6, 7, 6, 6 | Poster | Poster | ✔ |

2190 | Preserved central model for faster bidirectional compression in distributed settings | 5.80 | 0.40 | 5, 6, 6, 6, 6 | Poster | Poster | |

2191 | Evaluating model performance under worst-case subpopulations | 5.80 | 0.75 | 5, 5, 6, 6, 7 | Poster | Poster | |

2192 | Near Optimal Policy Optimization via REPS | 5.80 | 1.60 | 7, 4, 4, 8, 6 | Poster | Poster | |

2193 | Efficient Bayesian network structure learning via local Markov boundary search | 5.80 | 0.75 | 5, 7, 5, 6, 6 | Poster | Reject | ✔ |

2194 | Natural continual learning: success is a journey, not (just) a destination | 5.80 | 0.75 | 5, 6, 5, 6, 7 | Poster | Poster | |

2195 | On Optimal Interpolation in Linear Regression | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | |

2196 | Graph Neural Networks with Adaptive Residual | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2197 | Beyond Smoothness: Incorporating Low-Rank Analysis into Nonparametric Density Estimation | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2198 | Federated-EM with heterogeneity mitigation and variance reduction | 5.75 | 1.92 | 8, 7, 3, 5 | Poster | Poster | |

2199 | Tracking People with 3D Representations | 5.75 | 1.09 | 6, 4, 6, 7 | Poster | Poster | |

2200 | On the Out-of-distribution Generalization of Probabilistic Image Modelling | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2201 | Learning where to learn: Gradient sparsity in meta and continual learning | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | ✔ |

2202 | Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | ✔ |

2203 | On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources | 5.75 | 1.09 | 7, 6, 4, 6 | Poster | Reject | ✔ |

2204 | DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | ✔ |

2205 | NAS-Bench-x11 and the Power of Learning Curves | 5.75 | 0.83 | 6, 5, 5, 7 | Poster | Poster | |

2206 | Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2207 | Open Rule Induction | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Reject | ✔ |

2208 | Integrating Tree Path in Transformer for Code Representation | 5.75 | 1.09 | 6, 7, 6, 4 | Poster | Poster | ✔ |

2209 | Revealing and Protecting Labels in Distributed Training | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | |

2210 | Charting and Navigating the Space of Solutions for Recurrent Neural Networks | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | ✔ |

2211 | Self-Supervised GANs with Label Augmentation | 5.75 | 0.83 | 5, 7, 5, 6 | Poster | Poster | |

2212 | Fast Axiomatic Attribution for Neural Networks | 5.75 | 1.30 | 4, 7, 7, 5 | Poster | Poster | |

2213 | Probability Paths and the Structure of Predictions over Time | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | ✔ |

2214 | SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2215 | Structured Dropout Variational Inference for Bayesian Neural Networks | 5.75 | 0.83 | 7, 6, 5, 5 | Poster | Poster | |

2216 | Post-Training Quantization for Vision Transformer | 5.75 | 1.64 | 3, 7, 6, 7 | Poster | Poster | ✔ |

2217 | Center Smoothing: Certified Robustness for Networks with Structured Outputs | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2218 | Multi-View Representation Learning via Total Correlation Objective | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2219 | Multiple Descent: Design Your Own Generalization Curve | 5.75 | 1.64 | 7, 7, 3, 6 | Poster | Poster | |

2220 | Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2221 | RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2222 | Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2223 | Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks | 5.75 | 1.48 | 6, 8, 5, 4 | Poster | Poster | |

2224 | Limiting fluctuation and trajectorial stability of multilayer neural networks with mean field training | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | ✔ |

2225 | DeepGEM: Generalized Expectation-Maximization for Blind Inversion | 5.75 | 1.79 | 4, 7, 4, 8 | Poster | Poster | |

2226 | REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People under Weak Supervision | 5.75 | 1.09 | 4, 6, 7, 6 | Poster | Poster | |

2227 | OctField: Hierarchical Implicit Functions for 3D Modeling | 5.75 | 1.09 | 6, 7, 4, 6 | Poster | Poster | |

2228 | Towards Sample-efficient Overparameterized Meta-learning | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2229 | Can we globally optimize cross-validation loss? Quasiconvexity in ridge regression | 5.75 | 1.09 | 6, 4, 7, 6 | Poster | Poster | |

2230 | Scalable Thompson Sampling using Sparse Gaussian Process Models | 5.75 | 1.09 | 4, 6, 7, 6 | Poster | Poster | ✔ |

2231 | Fitting summary statistics of neural data with a differentiable spiking network simulator | 5.75 | 0.83 | 5, 7, 5, 6 | Poster | Poster | |

2232 | The Benefits of Implicit Regularization from SGD in Least Squares Problems | 5.75 | 0.83 | 6, 7, 5, 5 | Poster | Poster | |

2233 | On the Estimation Bias in Double Q-Learning | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | |

2234 | The Role of Global Labels in Few-Shot Classification and How to Infer Them | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2235 | Object-Centric Representation Learning with Generative Spatial-Temporal Factorization | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2236 | The Image Local Autoregressive Transformer | 5.75 | 1.09 | 6, 4, 6, 7 | Poster | Poster | |

2237 | SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2238 | Robust Compressed Sensing MRI with Deep Generative Priors | 5.75 | 1.09 | 4, 6, 6, 7 | Poster | Poster | |

2239 | Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data | 5.75 | 1.09 | 6, 6, 4, 7 | Poster | Poster | |

2240 | Shapley Residuals: Quantifying the limits of the Shapley value for explanations | 5.75 | 1.30 | 4, 5, 7, 7 | Poster | Poster | |

2241 | When Is Unsupervised Disentanglement Possible? | 5.75 | 1.09 | 7, 4, 6, 6 | Poster | Poster | |

2242 | STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Reject | ✔ |

2243 | Adaptive Denoising via GainTuning | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | ✔ |

2244 | Continuous Latent Process Flows | 5.75 | 1.79 | 7, 8, 4, 4 | Poster | Poster | |

2245 | On Success and Simplicity: A Second Look at Transferable Targeted Attacks | 5.75 | 1.09 | 6, 4, 7, 6 | Poster | Poster | ✔ |

2246 | Distributed Saddle-Point Problems Under Data Similarity | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Reject | ✔ |

2247 | Reformulating Zero-shot Action Recognition for Multi-label Actions | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2248 | A unified framework for bandit multiple testing | 5.75 | 0.83 | 6, 7, 5, 5 | Poster | Poster | |

2249 | Learning Graph Models for Retrosynthesis Prediction | 5.75 | 1.48 | 6, 8, 5, 4 | Poster | Poster | ✔ |

2250 | Efficient Training of Visual Transformers with Small Datasets | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Spotlight | ✔ |

2251 | A Winning Hand: Compressing Deep Networks Can Improve Out-of-Distribution Robustness | 5.75 | 1.09 | 4, 6, 7, 6 | Poster | Poster | |

2252 | Conditioning Sparse Variational Gaussian Processes for Online Decision-making | 5.75 | 0.83 | 5, 5, 6, 7 | Poster | Poster | |

2253 | End-to-end Multi-modal Video Temporal Grounding | 5.75 | 1.09 | 6, 7, 6, 4 | Poster | Poster | |

2254 | Grammar-Based Grounded Lexicon Learning | 5.75 | 1.64 | 7, 3, 7, 6 | Poster | Poster | ✔ |

2255 | Grammar-Based Grounded Lexicon Learning | 5.75 | 0.83 | 7, 5, 6, 5 | Poster | Poster | ✔ |

2256 | Exploring Social Posterior Collapse in Variational Autoencoder for Interaction Modeling | 5.75 | 1.09 | 6, 4, 6, 7 | Poster | Poster | |

2257 | Dueling Bandits with Team Comparisons | 5.75 | 0.83 | 5, 5, 7, 6 | Poster | Poster | |

2258 | Efficient Learning of Discrete-Continuous Computation Graphs | 5.75 | 1.09 | 6, 4, 7, 6 | Poster | Poster | ✔ |

2259 | A variational approximate posterior for the deep Wishart process | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2260 | Convex Polytope Trees and its Application to VAE | 5.75 | 1.79 | 8, 6, 6, 3 | Poster | Poster | |

2261 | Deep Learning with Label Differential Privacy | 5.75 | 1.48 | 4, 5, 8, 6 | Poster | Poster | |

2262 | Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families | 5.75 | 1.48 | 4, 8, 6, 5 | Poster | Reject | ✔ |

2263 | Dense Unsupervised Learning for Video Segmentation | 5.75 | 1.64 | 7, 7, 6, 3 | Poster | Poster | |

2264 | Unsupervised Object-Level Representation Learning from Scene Images | 5.75 | 1.09 | 7, 4, 6, 6 | Poster | Poster | |

2265 | Adversarial Robustness without Adversarial Training: A Teacher-Guided Curriculum Learning Approach | 5.75 | 0.83 | 5, 6, 5, 7 | Poster | Poster | |

2266 | Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2267 | Unsupervised Object-Based Transition Models For 3D Partially Observable Environments | 5.75 | 1.48 | 4, 5, 8, 6 | Poster | Reject | ✔ |

2268 | Understanding How Encoder-Decoder Architectures Attend | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2269 | On Episodes, Prototypical Networks, and Few-Shot Learning | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2270 | Design of Experiments for Stochastic Contextual Linear Bandits | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2271 | An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives | 5.75 | 0.83 | 6, 7, 5, 5 | Poster | Poster | |

2272 | Bandit Quickest Changepoint Detection | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Reject | ✔ |

2273 | Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations | 5.75 | 0.83 | 5, 5, 6, 7 | Poster | Poster | |

2274 | AutoGEL: An Automated Graph Neural Network with Explicit Link Information | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2275 | Detecting Moments and Highlights in Videos via Natural Language Queries | 5.75 | 0.83 | 6, 7, 5, 5 | Poster | Poster | |

2276 | Fair Sequential Selection Using Supervised Learning Models | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2277 | Learning Diverse Policies in MOBA Games via Macro-Goals | 5.75 | 0.83 | 6, 5, 5, 7 | Poster | Poster | |

2278 | Few-Shot Segmentation via Cycle-Consistent Transformer | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2279 | A Highly-Efficient Group Elastic Net Algorithm with an Application to Function-On-Scalar Regression | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | ✔ |

2280 | Glance-and-Gaze Vision Transformer | 5.75 | 1.64 | 7, 3, 7, 6 | Poster | Poster | |

2281 | POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples | 5.75 | 1.09 | 6, 7, 6, 4 | Poster | Poster | ✔ |

2282 | Towards Multi-Grained Explainability for Graph Neural Networks | 5.75 | 1.30 | 5, 7, 7, 4 | Poster | Reject | ✔ |

2283 | Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks | 5.75 | 1.30 | 7, 5, 4, 7 | Poster | Poster | |

2284 | Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation | 5.75 | 1.09 | 6, 4, 7, 6 | Poster | Poster | |

2285 | Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2286 | Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN | 5.75 | 1.79 | 6, 6, 8, 3 | Poster | Poster | |

2287 | Compressed Video Contrastive Learning | 5.75 | 1.09 | 7, 6, 4, 6 | Poster | Poster | ✔ |

2288 | Meta-Learning Reliable Priors in the Function Space | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | |

2289 | Learning-Augmented Dynamic Power Management with Multiple States via New Ski Rental Bounds | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | ✔ |

2290 | Matrix encoding networks for neural combinatorial optimization | 5.75 | 0.83 | 5, 5, 7, 6 | Poster | Poster | |

2291 | Coordinated Proximal Policy Optimization | 5.75 | 0.83 | 6, 5, 5, 7 | Poster | Poster | |

2292 | Fast Routing under Uncertainty: Adaptive Learning in Congestion Games via Exponential Weights | 5.75 | 0.43 | 6, 6, 5, 6 | Poster | Poster | |

2293 | Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Reject | ✔ |

2294 | Stochastic bandits with groups of similar arms. | 5.75 | 0.83 | 5, 7, 5, 6 | Poster | Poster | |

2295 | CogView: Mastering Text-to-Image Generation via Transformers | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2296 | Exploring Forensic Dental Identification with Deep Learning | 5.75 | 1.30 | 7, 4, 5, 7 | Poster | Poster | |

2297 | One Explanation is Not Enough: Structured Attention Graphs for Image Classification | 5.75 | 1.09 | 6, 7, 6, 4 | Poster | Poster | ✔ |

2298 | A mechanistic multi-area recurrent network model of decision-making | 5.75 | 1.79 | 7, 8, 4, 4 | Poster | Reject | ✔ |

2299 | Adversarial Examples Make Strong Poisons | 5.75 | 1.09 | 4, 7, 6, 6 | Poster | Poster | |

2300 | Controllable and Compositional Generation with Latent-Space Energy-Based Models | 5.75 | 1.09 | 7, 4, 6, 6 | Poster | Poster | |

2301 | Deformable Butterfly: A Highly Structured and Sparse Linear Transform | 5.75 | 1.09 | 6, 6, 7, 4 | Poster | Poster | ✔ |

2302 | Locally Valid and Discriminative Prediction Intervals for Deep Learning Models | 5.75 | 1.64 | 7, 7, 6, 3 | Poster | Poster | |

2303 | HyperSPNs: Compact and Expressive Probabilistic Circuits | 5.75 | 1.30 | 7, 4, 5, 7 | Poster | Poster | |

2304 | A nonparametric method for gradual change problems with statistical guarantees | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Reject | ✔ |

2305 | TriBERT: Human-centric Audio-visual Representation Learning | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2306 | Non-asymptotic convergence bounds for Wasserstein approximation using point clouds | 5.75 | 0.83 | 5, 5, 7, 6 | Poster | Reject | ✔ |

2307 | A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks | 5.75 | 0.83 | 5, 6, 5, 7 | Poster | Poster | |

2308 | Dynamical Wasserstein Barycenters for Time-series Modeling | 5.75 | 0.83 | 6, 5, 5, 7 | Poster | Poster | |

2309 | An Uncertainty Principle is a Price of Privacy-Preserving Microdata | 5.75 | 0.83 | 5, 6, 7, 5 | Poster | Poster | ✔ |

2310 | A No-go Theorem for Robust Acceleration in the Hyperbolic Plane | 5.75 | 1.30 | 7, 7, 5, 4 | Poster | Poster | |

2311 | On Component Interactions in Two-Stage Recommender Systems | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2312 | OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression | 5.75 | 1.79 | 4, 4, 8, 7 | Poster | Poster | |

2313 | Differentiable rendering with perturbed optimizers | 5.75 | 1.09 | 6, 4, 6, 7 | Poster | Poster | |

2314 | Cross-view Geo-localization with Layer-to-Layer Transformer | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | |

2315 | Numerical influence of ReLU’(0) on backpropagation | 5.75 | 1.64 | 3, 7, 7, 6 | Poster | Poster | |

2316 | Model-Based Episodic Memory Induces Dynamic Hybrid Controls | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | ✔ |

2317 | Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2318 | Provably Efficient Causal Reinforcement Learning with Confounded Observational Data | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2319 | Deep Conditional Gaussian Mixture Model for Constrained Clustering | 5.75 | 1.30 | 7, 4, 7, 5 | Poster | Poster | ✔ |

2320 | Deep Conditional Gaussian Mixture Model for Constrained Clustering | 5.75 | 1.09 | 7, 4, 6, 6 | Poster | Reject | ✔ |

2321 | Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression | 5.75 | 1.09 | 6, 7, 6, 4 | Poster | Poster | ✔ |

2322 | On Memorization in Probabilistic Deep Generative Models | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2323 | Mixture weights optimisation for Alpha-Divergence Variational Inference | 5.75 | 1.09 | 4, 6, 6, 7 | Poster | Poster | |

2324 | ResT: An Efficient Transformer for Visual Recognition | 5.75 | 0.43 | 6, 6, 6, 5 | Poster | Poster | |

2325 | Self-Supervised Multi-Object Tracking with Cross-input Consistency | 5.75 | 1.30 | 7, 7, 4, 5 | Poster | Poster | |

2326 | Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention | 5.75 | 1.64 | 7, 6, 3, 7 | Poster | Poster | |

2327 | Optimizing Reusable Knowledge for Continual Learning via Metalearning | 5.75 | 0.83 | 7, 6, 5, 5 | Poster | Reject | ✔ |

2328 | Large-Scale Wasserstein Gradient Flows | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2329 | Sparse Quadratic Optimisation over the Stiefel Manifold with Application to Permutation Synchronisation | 5.75 | 1.09 | 7, 6, 6, 4 | Poster | Poster | |

2330 | Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture | 5.75 | 0.83 | 5, 7, 6, 5 | Poster | Poster | |

2331 | Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters | 5.75 | 0.83 | 6, 5, 5, 7 | Poster | Poster | |

2332 | Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks | 5.75 | 0.43 | 6, 5, 6, 6 | Poster | Poster | |

2333 | Post-Training Sparsity-Aware Quantization | 5.75 | 0.83 | 7, 5, 5, 6 | Poster | Poster | |

2334 | Momentum Centering and Asynchronous Update for Adaptive Gradient Methods | 5.75 | 0.83 | 5, 5, 6, 7 | Poster | Poster | |

2335 | Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering | 5.75 | 0.83 | 6, 5, 7, 5 | Poster | Poster | ✔ |

2336 | MLP-Mixer: An all-MLP Architecture for Vision | 5.75 | 0.43 | 5, 6, 6, 6 | Poster | Poster | |

2337 | Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving | 5.75 | 1.09 | 7, 4, 6, 6 | Poster | Poster | |

2338 | Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages | 5.75 | 1.09 | 4, 7, 6, 6 | Poster | Poster | |

2339 | Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer | 5.75 | 1.30 | 7, 7, 4, 5 | Poster | Poster | ✔ |

2340 | Grounding Spatio-Temporal Language with Transformers | 5.75 | 1.09 | 4, 7, 6, 6 | Poster | Poster | ✔ |

2341 | Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks | 5.75 | 1.30 | 5, 8, 5, 5 | Poster | Poster | |

2342 | On the Value of Infinite Gradients in Variational Autoencoder Models | 5.75 | 0.43 | 6, 5, 6, 6 | Spotlight | Reject | ✔ |

2343 | Two steps to risk sensitivity | 5.75 | 1.48 | 5, 4, 8, 6 | Spotlight | Spotlight | |

2344 | Finite Sample Analysis of Average-Reward TD Learning and
Q
-Learning | 5.67 | 0.94 | 5, 5, 7 | Poster | Reject | ✔ |

2345 | Asymptotics of the Bootstrap via Stability with Applications to Inference with Model Selection | 5.67 | 0.94 | 5, 5, 7 | Poster | Reject | ✔ |

2346 | Learning Signal-Agnostic Implicit Manifolds | 5.67 | 0.47 | 6, 5, 6 | Poster | Poster | |

2347 | Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals | 5.67 | 0.47 | 6, 6, 5 | Poster | Poster | |

2348 | Rethinking Neural Operations for Diverse Tasks | 5.67 | 1.89 | 7, 3, 7 | Poster | Poster | |

2349 | INDIGO: GNN-Based Inductive Knowledge Graph Completion Using Pair-Wise Encoding | 5.67 | 0.47 | 6, 6, 5 | Poster | Poster | |

2350 | FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition | 5.67 | 0.47 | 6, 5, 6 | Poster | Poster | |

2351 | Teaching an Active Learner with Contrastive Examples | 5.67 | 0.47 | 5, 6, 6 | Poster | Poster | |

2352 | Fast Certified Robust Training with Short Warmup | 5.67 | 0.47 | 6, 5, 6 | Poster | Poster | ✔ |

2353 | Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis | 5.67 | 1.25 | 4, 7, 6 | Poster | Poster | |

2354 | Contextual Recommendations and Low-Regret Cutting-Plane Algorithms | 5.67 | 2.05 | 6, 3, 8 | Poster | Reject | ✔ |

2355 | SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning | 5.67 | 1.25 | 7, 4, 6 | Poster | Poster | |

2356 | IA-RED
2
: Interpretability-Aware Redundancy Reduction for Vision Transformers | 5.67 | 1.25 | 7, 6, 4 | Poster | Poster | |

2357 | Batch Active Learning at Scale | 5.67 | 2.05 | 3, 8, 6 | Poster | Poster | |

2358 | Pooling by Sliced-Wasserstein Embedding | 5.67 | 1.70 | 5, 8, 4 | Poster | Reject | ✔ |

2359 | Gaussian Kernel Mixture Network for Single Image Defocus Deblurring | 5.67 | 1.25 | 7, 4, 6 | Poster | Reject | ✔ |

2360 | Dataset Distillation with Infinitely Wide Convolutional Networks | 5.67 | 0.47 | 5, 6, 6 | Poster | Reject | ✔ |

2361 | Deep Neural Networks as Point Estimates for Deep Gaussian Processes | 5.67 | 0.94 | 5, 5, 7 | Poster | Poster | |

2362 | Referring Transformer: A One-step Approach to Multi-task Visual Grounding | 5.67 | 0.94 | 5, 7, 5 | Poster | Reject | ✔ |

2363 | Bandit Quickest Changepoint Detection | 5.67 | 0.94 | 5, 7, 5 | Poster | Poster | ✔ |

2364 | Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion | 5.67 | 0.47 | 5, 6, 6 | Poster | Poster | ✔ |

2365 | Multimodal Virtual Point 3D Detection | 5.67 | 1.25 | 4, 7, 6 | Poster | Poster | |

2366 | Speech-T: Transducer for Text to Speech and Beyond | 5.67 | 0.47 | 5, 6, 6 | Poster | Poster | |

2367 | Learning with Labeling Induced Abstentions | 5.67 | 0.47 | 6, 5, 6 | Poster | Poster | |

2368 | Neural Bootstrapper | 5.67 | 1.89 | 7, 3, 7 | Poster | Poster | |

2369 | On the Provable Generalization of Recurrent Neural Networks | 5.67 | 0.47 | 6, 6, 5 | Poster | Poster | |

2370 | Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels | 5.67 | 1.25 | 7, 4, 6 | Poster | Poster | |

2371 | PettingZoo: Gym for Multi-Agent Reinforcement Learning | 5.67 | 0.94 | 7, 5, 5 | Poster | Poster | |

2372 | Reinforcement Learning Enhanced Explainer for Graph Neural Networks | 5.67 | 0.47 | 6, 5, 6 | Poster | Poster | |

2373 | Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling | 5.67 | 1.25 | 6, 7, 4 | Poster | Poster | |

2374 | Disrupting Deep Uncertainty Estimation Without Harming Accuracy | 5.67 | 0.94 | 7, 5, 5 | Poster | Reject | ✔ |

2375 | Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning | 5.67 | 0.47 | 6, 6, 5 | Poster | Poster | |

2376 | Topographic VAEs learn Equivariant Capsules | 5.67 | 0.47 | 6, 6, 5 | Poster | Poster | |

2377 | A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning | 5.67 | 0.47 | 6, 6, 5 | Poster | Reject | ✔ |

2378 | Making the most of your day: online learning for optimal allocation of time | 5.67 | 1.25 | 7, 4, 6 | Poster | Poster | |

2379 | Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection | 5.67 | 0.47 | 6, 6, 5 | Poster | Poster | |

2380 | Progressive Coordinate Transforms for Monocular 3D Object Detection | 5.67 | 2.05 | 6, 8, 3 | Poster | Poster | |

2381 | What can linearized neural networks actually say about generalization? | 5.67 | 0.94 | 7, 5, 5 | Poster | Poster | |

2382 | Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement | 5.67 | 0.47 | 6, 5, 6 | Poster | Poster | |

2383 | Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach | 5.60 | 1.50 | 3, 6, 7, 7, 5 | Poster | Reject | ✔ |

2384 | CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration | 5.60 | 1.02 | 5, 4, 6, 7, 6 | Poster | Poster | |

2385 | Locally differentially private estimation of functionals of discrete distributions | 5.60 | 0.80 | 6, 7, 5, 5, 5 | Poster | Reject | ✔ |

2386 | Risk-Averse Bayes-Adaptive Reinforcement Learning | 5.60 | 1.02 | 6, 7, 5, 4, 6 | Poster | Reject | ✔ |

2387 | Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback | 5.60 | 1.02 | 7, 6, 6, 4, 5 | Poster | Poster | |

2388 | Conformal Bayesian Computation | 5.60 | 1.36 | 7, 4, 6, 7, 4 | Poster | Poster | |

2389 | Fast and accurate randomized algorithms for low-rank tensor decompositions | 5.60 | 0.49 | 6, 6, 6, 5, 5 | Poster | Poster | |

2390 | Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems | 5.60 | 1.50 | 7, 7, 5, 3, 6 | Poster | Poster | |

2391 | An Improved Analysis of Gradient Tracking for Decentralized Machine Learning | 5.50 | 1.66 | 4, 8, 4, 6 | Poster | Poster | |

2392 | Non-local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation | 5.50 | 0.87 | 6, 6, 6, 4 | Poster | Poster | |

2393 | Decoupling the Depth and Scope of Graph Neural Networks | 5.50 | 1.12 | 6, 5, 7, 4 | Poster | Reject | ✔ |

2394 | XDO: A Double Oracle Algorithm for Extensive-Form Games | 5.50 | 0.50 | 5, 6, 6, 5 | Poster | Poster | ✔ |

2395 | Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks | 5.50 | 0.50 | 6, 5, 6, 5 | Poster | Poster | |

2396 | UCB-based Algorithms for Multinomial Logistic Regression Bandits | 5.50 | 0.50 | 5, 5, 6, 6 | Poster | Poster | |

2397 | Probability Paths and the Structure of Predictions over Time | 5.50 | 0.87 | 7, 5, 5, 5 | Poster | Reject | ✔ |

2398 | Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization | 5.50 | 0.87 | 4, 6, 6, 6 | Poster | Poster | |

2399 | Low-Rank Constraints for Fast Inference in Structured Models | 5.50 | 1.12 | 5, 6, 4, 7 | Poster | Reject | ✔ |

2400 | Fast Doubly-Adaptive MCMC to Estimate the Gibbs Partition Function with Weak Mixing Time Bounds | 5.50 | 1.12 | 5, 6, 4, 7 | Poster | Poster | |

2401 | TNASP: A Transformer-based NAS Predictor with a Self-evolution Framework | 5.50 | 0.50 | 6, 5, 5, 6 | Poster | Poster | |

2402 | Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models | 5.50 | 0.50 | 5, 6, 5, 6 | Poster | Poster | ✔ |

2403 | Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning | 5.50 | 1.12 | 5, 7, 6, 4 | Poster | Poster | |

2404 | Meta-learning to Improve Pre-training | 5.50 | 0.50 | 5, 6, 5, 6 | Poster | Poster | |

2405 | MobILE: Model-Based Imitation Learning From Observation Alone | 5.50 | 0.87 | 6, 6, 4, 6 | Poster | Poster | |

2406 | UniDoc: Unified Pretraining Framework for Document Understanding | 5.50 | 0.87 | 6, 4, 6, 6 | Poster | Poster | |

2407 | A/B/n Testing with Control in the Presence of Subpopulations | 5.50 | 0.87 | 5, 5, 7, 5 | Poster | Poster | |

2408 | Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection | 5.50 | 0.87 | 6, 4, 6, 6 | Poster | Poster | |

2409 | Sharp Impossibility Results for Hyper-graph Testing | 5.50 | 0.50 | 5, 5, 6, 6 | Poster | Poster | |

2410 | Biological key-value memory networks | 5.50 | 0.50 | 6, 5, 5, 6 | Poster | Reject | ✔ |

2411 | Space-time Mixing Attention for Video Transformer | 5.50 | 0.87 | 4, 6, 6, 6 | Poster | Poster | |

2412 | Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent | 5.50 | 1.12 | 5, 6, 7, 4 | Poster | Poster | |

2413 | Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation | 5.50 | 1.12 | 5, 6, 4, 7 | Poster | Poster | |

2414 | Dataset Distillation with Infinitely Wide Convolutional Networks | 5.50 | 0.50 | 6, 5, 6, 5 | Poster | Poster | ✔ |

2415 | ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions | 5.50 | 0.87 | 7, 5, 5, 5 | Poster | Reject | ✔ |

2416 | Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning | 5.50 | 1.50 | 6, 3, 7, 6 | Poster | Poster | |

2417 | STORM+: Fully Adaptive SGD with Recursive Momentum for Nonconvex Optimization | 5.50 | 0.50 | 5, 6, 6, 5 | Poster | Poster | |

2418 | A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning | 5.50 | 0.50 | 6, 5, 6, 5 | Poster | Reject | ✔ |

2419 | Post-processing for Individual Fairness | 5.50 | 1.12 | 4, 6, 5, 7 | Poster | Reject | ✔ |

2420 | Offline Model-based Adaptable Policy Learning | 5.50 | 0.87 | 6, 6, 4, 6 | Poster | Poster | |

2421 | Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints | 5.50 | 0.50 | 5, 6, 6, 5 | Poster | Reject | ✔ |

2422 | Going Beyond Linear RL: Sample Efficient Neural Function Approximation | 5.50 | 1.50 | 6, 3, 7, 6 | Poster | Poster | |

2423 | On Locality of Local Explanation Models | 5.50 | 1.50 | 7, 6, 6, 3 | Poster | Reject | ✔ |

2424 | Differentially Private Federated Bayesian Optimization with Distributed Exploration | 5.50 | 0.50 | 5, 5, 6, 6 | Poster | Reject | ✔ |

2425 | Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning | 5.50 | 0.87 | 6, 6, 6, 4 | Poster | Reject | ✔ |

2426 | Dual Progressive Prototype Network for Generalized Zero-Shot Learning | 5.50 | 0.50 | 6, 6, 5, 5 | Poster | Reject | ✔ |

2427 | A PAC-Bayes Analysis of Adversarial Robustness | 5.50 | 0.87 | 6, 6, 6, 4 | Poster | Reject | ✔ |

2428 | Reconstruction for Powerful Graph Representations | 5.50 | 1.12 | 4, 5, 6, 7 | Poster | Poster | |

2429 | Faster Non-asymptotic Convergence for Double Q-learning | 5.50 | 1.12 | 6, 7, 5, 4 | Poster | Reject | ✔ |

2430 | Class-Incremental Learning via Dual Augmentation | 5.50 | 0.87 | 6, 6, 4, 6 | Poster | Poster | |

2431 | Evaluating State-of-the-Art Classification Models Against Bayes Optimality | 5.50 | 0.50 | 5, 6, 6, 5 | Poster | Reject | ✔ |

2432 | Adversarial Attack Generation Empowered by Min-Max Optimization | 5.50 | 0.96 | 5, 6, 4, 6, 7, 5 | Poster | Poster | |

2433 | On the Theory of Reinforcement Learning with Once-per-Episode Feedback | 5.50 | 1.12 | 4, 7, 6, 5 | Poster | Poster | ✔ |

2434 | A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast | 5.50 | 2.06 | 7, 7, 2, 6 | Poster | Poster | |

2435 | Hyperparameter Optimization Is Deceiving Us, and How to Stop It | 5.50 | 1.12 | 5, 4, 7, 6 | Poster | Poster | |

2436 | Continuous Doubly Constrained Batch Reinforcement Learning | 5.50 | 0.50 | 6, 6, 5, 5 | Poster | Reject | ✔ |

2437 | Beyond the Signs: Nonparametric Tensor Completion via Sign Series | 5.50 | 1.12 | 6, 5, 7, 4 | Poster | Poster | |

2438 | Fast and Memory Efficient Differentially Private-SGD via JL Projections | 5.50 | 1.50 | 7, 3, 6, 6 | Poster | Poster | |

2439 | Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations | 5.50 | 0.87 | 6, 6, 6, 4 | Poster | Poster | |

2440 | GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement | 5.50 | 1.12 | 7, 6, 5, 4 | Poster | Reject | ✔ |

2441 | Multilingual Pre-training with Universal Dependency Learning | 5.50 | 1.12 | 6, 7, 5, 4 | Poster | Reject | ✔ |

2442 | How Data Augmentation affects Optimization for Linear Regression | 5.50 | 1.50 | 3, 6, 6, 7 | Poster | Poster | |

2443 | Fast Training of Neural Lumigraph Representations using Meta Learning | 5.50 | 1.80 | 3, 8, 6, 5 | Poster | Poster | |

2444 | Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation | 5.50 | 0.50 | 5, 6, 6, 5 | Poster | Reject | ✔ |

2445 | Contrastive Reinforcement Learning of Symbolic Reasoning Domains | 5.50 | 1.12 | 4, 6, 7, 5 | Poster | Poster | |

2446 | Diffusion Normalizing Flow | 5.50 | 1.66 | 8, 4, 6, 4 | Poster | Poster | |

2447 | Exploiting Domain-Specific Features to Enhance Domain Generalization | 5.50 | 1.12 | 5, 7, 6, 4 | Poster | Reject | ✔ |

2448 | Variational Bayesian Reinforcement Learning with Regret Bounds | 5.50 | 0.87 | 6, 6, 4, 6 | Poster | Poster | |

2449 | Artistic Style Transfer with Internal-external Learning and Contrastive Learning | 5.50 | 1.50 | 6, 3, 7, 6 | Poster | Poster | |

2450 | Optimizing Reusable Knowledge for Continual Learning via Metalearning | 5.50 | 0.50 | 5, 6, 5, 6 | Poster | Poster | ✔ |

2451 | BCORLE(
λ
): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market | 5.50 | 1.12 | 4, 6, 7, 5 | Poster | Reject | ✔ |

2452 | Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization | 5.50 | 1.12 | 7, 4, 5, 6 | Poster | Reject | ✔ |

2453 | Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation | 5.50 | 0.87 | 6, 4, 6, 6 | Poster | Poster | ✔ |

2454 | Grounding Spatio-Temporal Language with Transformers | 5.50 | 1.12 | 4, 6, 7, 5 | Poster | Reject | ✔ |

2455 | Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning | 5.50 | 0.50 | 6, 5, 5, 6 | Spotlight | Reject | ✔ |

2456 | Generic Neural Architecture Search via Regression | 5.50 | 1.50 | 6, 6, 3, 7 | Spotlight | Spotlight | |

2457 | Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks | 5.50 | 1.50 | 7, 6, 6, 3 | Spotlight | Poster | ✔ |

2458 | Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence | 5.40 | 1.02 | 5, 4, 6, 7, 5 | Poster | Poster | |

2459 | Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks | 5.40 | 1.36 | 7, 3, 6, 5, 6 | Poster | Poster | |

2460 | Coupled Gradient Estimators for Discrete Latent Variables | 5.40 | 0.80 | 6, 5, 6, 4, 6 | Poster | Poster | ✔ |

2461 | Efficient Training of Visual Transformers with Small Datasets | 5.40 | 1.02 | 5, 4, 7, 6, 5 | Poster | Reject | ✔ |

2462 | On Robust Optimal Transport: Computational Complexity and Barycenter Computation | 5.40 | 0.80 | 5, 6, 6, 4, 6 | Poster | Poster | |

2463 | Efficient Neural Network Training via Forward and Backward Propagation Sparsification | 5.40 | 1.36 | 4, 7, 5, 7, 4 | Poster | Poster | |

2464 | Nested Graph Neural Networks | 5.40 | 1.20 | 6, 4, 7, 4, 6 | Poster | Poster | |

2465 | Navigating to the Best Policy in Markov Decision Processes | 5.40 | 0.80 | 6, 6, 4, 6, 5 | Poster | Poster | |

2466 | Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear Models | 5.40 | 0.80 | 6, 4, 6, 6, 5 | Poster | Poster | |

2467 | One More Step Towards Reality: Cooperative Bandits with Imperfect Communication | 5.33 | 0.47 | 6, 5, 5 | Poster | Reject | ✔ |

2468 | Domain Invariant Representation Learning with Domain Density Transformations | 5.33 | 0.94 | 6, 6, 4 | Poster | Poster | |

2469 | How does a Neural Network's Architecture Impact its Robustness to Noisy Labels? | 5.33 | 1.70 | 6, 7, 3 | Poster | Reject | ✔ |

2470 | Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning | 5.33 | 0.94 | 6, 6, 4 | Poster | Poster | ✔ |

2471 | Asymptotically Best Causal Effect Identification with Multi-Armed Bandits | 5.33 | 1.25 | 7, 4, 5 | Poster | Poster | ✔ |

2472 | Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification | 5.33 | 0.94 | 6, 6, 4 | Poster | Reject | ✔ |

2473 | An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning | 5.33 | 0.47 | 5, 5, 6 | Poster | Poster | |

2474 | Exponential Separation between Two Learning Models and Adversarial Robustness | 5.33 | 0.47 | 5, 6, 5 | Poster | Reject | ✔ |

2475 | Discrete-Valued Neural Communication | 5.33 | 2.36 | 7, 2, 7 | Poster | Poster | |

2476 | Nested Variational Inference | 5.33 | 0.47 | 6, 5, 5 | Poster | Reject | ✔ |

2477 | Adversarial Training Helps Transfer Learning via Better Representations | 5.33 | 0.47 | 5, 6, 5 | Poster | Poster | |

2478 | On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning | 5.33 | 0.94 | 6, 6, 4 | Poster | Poster | |

2479 | Deep Explicit Duration Switching Models for Time Series | 5.33 | 1.25 | 5, 7, 4 | Poster | Poster | |

2480 | ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias | 5.33 | 0.47 | 5, 5, 6 | Poster | Reject | ✔ |

2481 | Distilling Image Classifiers in Object Detectors | 5.33 | 1.25 | 5, 4, 7 | Poster | Poster | |

2482 | Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection | 5.33 | 0.47 | 6, 5, 5 | Poster | Reject | ✔ |

2483 | Spot the Difference: Detection of Topological Changes via Geometric Alignment | 5.33 | 1.25 | 5, 7, 4 | Poster | Poster | |

2484 | Low-Fidelity Video Encoder Optimization for Temporal Action Localization | 5.33 | 0.47 | 5, 6, 5 | Poster | Reject | ✔ |

2485 | Topology-Imbalance Learning for Semi-Supervised Node Classification | 5.33 | 0.47 | 5, 6, 5 | Poster | Reject | ✔ |

2486 | Predicting Deep Neural Network Generalization with Perturbation Response Curves | 5.33 | 2.05 | 8, 5, 3 | Poster | Poster | |

2487 | Dimensionality Reduction for Wasserstein Barycenter | 5.33 | 1.70 | 3, 6, 7 | Poster | Reject | ✔ |

2488 | Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation | 5.33 | 2.05 | 3, 5, 8 | Poster | Poster | |

2489 | The Emergence of Objectness: Learning Zero-shot Segmentation from Videos | 5.25 | 0.43 | 5, 6, 5, 5 | Poster | Poster | |

2490 | Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel | 5.25 | 0.83 | 5, 4, 6, 6 | Poster | Poster | |

2491 | DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Reject | ✔ |

2492 | Identifiability in inverse reinforcement learning | 5.25 | 0.83 | 4, 6, 5, 6 | Poster | Poster | |

2493 | Multi-Person 3D Motion Prediction with Multi-Range Transformers | 5.25 | 0.83 | 6, 5, 4, 6 | Poster | Reject | ✔ |

2494 | Faster Directional Convergence of Linear Neural Networks under Spherically Symmetric Data | 5.25 | 0.83 | 6, 4, 6, 5 | Poster | Poster | |

2495 | Associative Memories via Predictive Coding | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Poster | |

2496 | Post-Training Quantization for Vision Transformer | 5.25 | 0.83 | 4, 6, 6, 5 | Poster | Reject | ✔ |

2497 | Constrained Two-step Look-Ahead Bayesian Optimization | 5.25 | 0.83 | 6, 4, 5, 6 | Poster | Reject | ✔ |

2498 | NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild | 5.25 | 0.83 | 5, 6, 6, 4 | Poster | Poster | |

2499 | Row-clustering of a Point Process-valued Matrix | 5.25 | 1.09 | 4, 7, 5, 5 | Poster | Reject | ✔ |

2500 | SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios | 5.25 | 0.43 | 6, 5, 5, 5 | Poster | Reject | ✔ |

2501 | ErrorCompensatedX: error compensation for variance reduced algorithms | 5.25 | 0.43 | 5, 6, 5, 5 | Poster | Reject | ✔ |

2502 | Do Vision Transformers See Like Convolutional Neural Networks? | 5.25 | 0.83 | 5, 6, 6, 4 | Poster | Reject | ✔ |

2503 | Differentially Private Learning with Adaptive Clipping | 5.25 | 0.83 | 5, 4, 6, 6 | Poster | Poster | |

2504 | Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems | 5.25 | 1.48 | 7, 5, 3, 6 | Poster | Poster | |

2505 | End-to-End Weak Supervision | 5.25 | 0.43 | 5, 5, 5, 6 | Poster | Poster | |

2506 | Entropic Desired Dynamics for Intrinsic Control | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Reject | ✔ |

2507 | On the Equivalence between Neural Network and Support Vector Machine | 5.25 | 0.83 | 5, 4, 6, 6 | Poster | Poster | |

2508 | Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning | 5.25 | 0.83 | 6, 5, 4, 6 | Poster | Reject | ✔ |

2509 | Reusing Combinatorial Structure: Faster Iterative Projections over Submodular Base Polytopes | 5.25 | 0.83 | 6, 5, 4, 6 | Poster | Reject | ✔ |

2510 | Efficient Learning of Discrete-Continuous Computation Graphs | 5.25 | 1.09 | 4, 5, 7, 5 | Poster | Reject | ✔ |

2511 | Stochastic Online Linear Regression: the Forward Algorithm to Replace Ridge | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Reject | ✔ |

2512 | Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces | 5.25 | 1.30 | 6, 4, 7, 4 | Poster | Reject | ✔ |

2513 | Gaussian Kernel Mixture Network for Single Image Defocus Deblurring | 5.25 | 1.48 | 3, 6, 7, 5 | Poster | Poster | ✔ |

2514 | How to transfer algorithmic reasoning knowledge to learn new algorithms? | 5.25 | 0.83 | 6, 5, 4, 6 | Poster | Poster | |

2515 | Rethinking the Variational Interpretation of Accelerated Optimization Methods | 5.25 | 1.30 | 4, 6, 4, 7 | Poster | Poster | |

2516 | Rethinking the Pruning Criteria for Convolutional Neural Network | 5.25 | 1.30 | 4, 7, 6, 4 | Poster | Poster | |

2517 | Reinforcement learning for optimization of variational quantum circuit architectures | 5.25 | 1.30 | 6, 4, 4, 7 | Poster | Poster | |

2518 | NeRV: Neural Representations for Videos | 5.25 | 1.09 | 7, 4, 5, 5 | Poster | Poster | |

2519 | Shift Invariance Can Reduce Adversarial Robustness | 5.25 | 1.30 | 6, 6, 6, 3 | Poster | Poster | |

2520 | An online passive-aggressive algorithm for difference-of-squares classification | 5.25 | 1.48 | 3, 6, 5, 7 | Poster | Poster | |

2521 | Achieving Rotational Invariance with Bessel-Convolutional Neural Networks | 5.25 | 1.64 | 5, 4, 8, 4 | Poster | Reject | ✔ |

2522 | Shared Independent Component Analysis for Multi-Subject Neuroimaging | 5.25 | 0.83 | 6, 4, 5, 6 | Poster | Poster | ✔ |

2523 | Sim and Real: Better Together | 5.25 | 1.30 | 7, 6, 4, 4 | Poster | Poster | |

2524 | Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression | 5.25 | 1.64 | 4, 4, 5, 8 | Poster | Reject | ✔ |

2525 | Low-Rank Extragradient Method for Nonsmooth and Low-Rank Matrix Optimization Problems | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Reject | ✔ |

2526 | Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks | 5.25 | 1.30 | 4, 4, 6, 7 | Poster | Poster | |

2527 | Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Reject | ✔ |

2528 | Localization with Sampling-Argmax | 5.25 | 1.09 | 5, 7, 5, 4 | Poster | Reject | ✔ |

2529 | Locally private online change point detection | 5.25 | 1.48 | 3, 7, 5, 6 | Poster | Reject | ✔ |

2530 | Learning from Inside: Self-driven Siamese Sampling and Reasoning for Video Question Answering | 5.25 | 0.43 | 5, 5, 6, 5 | Poster | Reject | ✔ |

2531 | Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation | 5.25 | 0.43 | 5, 5, 6, 5 | Spotlight | Reject | ✔ |

2532 | Adversarial Robustness with Non-uniform Perturbations | 5.20 | 0.40 | 5, 5, 5, 6, 5 | Poster | Reject | ✔ |

2533 | VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text | 5.20 | 0.98 | 6, 6, 4, 4, 6 | Poster | Poster | |

2534 | Gradient Starvation: A Learning Proclivity in Neural Networks | 5.20 | 1.60 | 4, 5, 7, 7, 3 | Poster | Reject | ✔ |

2535 | Skipping the Frame-Level: Event-Based Piano Transcription With Neural Semi-CRFs | 5.00 | 0.71 | 5, 6, 5, 4 | Poster | Reject | ✔ |

2536 | SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL | 5.00 | 0.71 | 4, 5, 5, 6 | Poster | Reject | ✔ |

2537 | VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media | 5.00 | 0.71 | 4, 5, 5, 6 | Poster | Reject | ✔ |

2538 | Generalized DataWeighting via Class-Level Gradient Manipulation | 5.00 | 0.00 | 5, 5, 5, 5 | Poster | Reject | ✔ |

2539 | Integrating Tree Path in Transformer for Code Representation | 5.00 | 1.41 | 4, 4, 7 | Poster | Reject | ✔ |

2540 | Towards a Theoretical Framework of Out-of-Distribution Generalization | 5.00 | 0.71 | 5, 4, 6, 5 | Poster | Reject | ✔ |

2541 | Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence | 5.00 | 2.16 | 6, 7, 2 | Poster | Poster | |

2542 | Handling Long-tailed Feature Distribution in AdderNets | 5.00 | 0.71 | 5, 5, 6, 4 | Poster | Reject | ✔ |

2543 | The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations | 5.00 | 1.22 | 5, 3, 6, 6 | Poster | Poster | |

2544 | An Empirical Study of Adder Neural Networks for Object Detection | 5.00 | 1.63 | 7, 5, 3 | Poster | Reject | ✔ |

2545 | An Empirical Study of Adder Neural Networks for Object Detection | 5.00 | 0.71 | 6, 4, 5, 5 | Poster | Poster | ✔ |

2546 | Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training | 5.00 | 1.22 | 5, 7, 4, 4 | Poster | Reject | ✔ |

2547 | Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning | 5.00 | 1.58 | 4, 7, 6, 3 | Poster | Reject | ✔ |

2548 | Efficient Active Learning for Gaussian Process Classification by Error Reduction | 5.00 | 0.00 | 5, 5, 5 | Poster | Reject | ✔ |

2549 | Distributionally Robust Imitation Learning | 5.00 | 0.71 | 6, 5, 5, 4 | Poster | Reject | ✔ |

2550 | Adversarial Reweighting for Partial Domain Adaptation | 5.00 | 0.00 | 5, 5, 5 | Poster | Reject | ✔ |

2551 | Accelerating Quadratic Optimization with Reinforcement Learning | 5.00 | 2.45 | 5, 1, 7, 7 | Poster | Poster | ✔ |

2552 | Online Knapsack with Frequency Predictions | 5.00 | 1.41 | 4, 4, 7 | Poster | Reject | ✔ |

2553 | PolarStream: Streaming Object Detection and Segmentation with Polar Pillars | 5.00 | 0.00 | 5, 5, 5 | Poster | Reject | ✔ |

2554 | Meta-Adaptive Nonlinear Control: Theory and Algorithms | 5.00 | 1.00 | 4, 6, 6, 4 | Poster | Reject | ✔ |

2555 | On Contrastive Representations of Stochastic Processes | 5.00 | 0.71 | 5, 4, 6, 5 | Poster | Poster | |

2556 | Pipeline Combinators for Gradual AutoML | 5.00 | 1.87 | 3, 8, 5, 4 | Poster | Reject | ✔ |

2557 | Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion | 5.00 | 0.00 | 5, 5, 5, 5 | Poster | Reject | ✔ |

2558 | Observation-Free Attacks on Stochastic Bandits | 5.00 | 0.82 | 4, 5, 6 | Poster | Poster | |

2559 | Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote | 5.00 | 0.00 | 5, 5, 5, 5 | Poster | Reject | ✔ |

2560 | POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples | 5.00 | 0.71 | 5, 6, 5, 4 | Poster | Reject | ✔ |

2561 | Directed Graph Contrastive Learning | 5.00 | 0.71 | 5, 4, 6, 5 | Poster | Reject | ✔ |

2562 | The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle | 5.00 | 1.22 | 4, 5, 4, 7 | Poster | Reject | ✔ |

2563 | Automated Discovery of Adaptive Attacks on Adversarial Defenses | 5.00 | 0.71 | 5, 4, 5, 6 | Poster | Poster | |

2564 | FACMAC: Factored Multi-Agent Centralised Policy Gradients | 5.00 | 2.83 | 7, 1, 7 | Poster | Reject | ✔ |

2565 | On the Theory of Reinforcement Learning with Once-per-Episode Feedback | 5.00 | 0.71 | 4, 5, 5, 6 | Poster | Reject | ✔ |

2566 | CoAtNet: Marrying Convolution and Attention for All Data Sizes | 5.00 | 0.71 | 5, 6, 5, 4 | Poster | Reject | ✔ |

2567 | Conditional Generation Using Polynomial Expansions | 5.00 | 1.22 | 4, 5, 7, 4 | Poster | Reject | ✔ |

2568 | Continuous vs. Discrete Optimization of Deep Neural Networks | 5.00 | 1.58 | 6, 7, 3, 4 | Spotlight | Reject | ✔ |

2569 | Learning Disentangled Behavior Embeddings | 5.00 | 0.82 | 5, 6, 4 | Spotlight | Reject | ✔ |

2570 | Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models | 4.80 | 0.98 | 4, 4, 6, 4, 6 | Poster | Reject | ✔ |

2571 | Program Synthesis Guided Reinforcement Learning for Partially Observed Environments | 4.80 | 1.17 | 5, 4, 4, 4, 7 | Spotlight | Reject | ✔ |

2572 | Directional Message Passing on Molecular Graphs via Synthetic Coordinates | 4.75 | 1.30 | 3, 6, 4, 6 | Poster | Poster | |

2573 | Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs | 4.75 | 0.43 | 5, 4, 5, 5 | Poster | Reject | ✔ |

2574 | Machine versus Human Attention in Deep Reinforcement Learning Tasks | 4.75 | 1.48 | 7, 5, 3, 4 | Poster | Reject | ✔ |

2575 | Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization | 4.75 | 1.30 | 6, 4, 6, 3 | Poster | Reject | ✔ |

2576 | Parallelizing Thompson Sampling | 4.75 | 1.09 | 6, 3, 5, 5 | Poster | Reject | ✔ |

2577 | Machine learning structure preserving brackets for forecasting irreversible processes | 4.75 | 1.09 | 5, 5, 6, 3 | Poster | Reject | ✔ |

2578 | Distributional Reinforcement Learning for Multi-Dimensional Reward Functions | 4.75 | 1.09 | 5, 3, 6, 5 | Poster | Reject | ✔ |

2579 | Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing | 4.75 | 0.83 | 6, 5, 4, 4 | Poster | Reject | ✔ |

2580 | Learning to Generate Visual Questions with Noisy Supervision | 4.75 | 0.43 | 5, 5, 4, 5 | Poster | Reject | ✔ |

2581 | Residual2Vec: Debiasing graph embedding with random graphs | 4.75 | 0.83 | 6, 4, 5, 4 | Poster | Reject | ✔ |

2582 | Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks | 4.75 | 0.83 | 4, 4, 5, 6 | Poster | Poster | |

2583 | A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs | 4.75 | 1.48 | 3, 5, 4, 7 | Poster | Poster | |

2584 | Emergent Discrete Communication in Semantic Spaces | 4.75 | 0.83 | 4, 6, 4, 5 | Poster | Reject | ✔ |

2585 | FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention | 4.75 | 0.83 | 4, 4, 5, 6 | Poster | Poster | |

2586 | SBO-RNN: Reformulating Recurrent Neural Networks via Stochastic Bilevel Optimization | 4.75 | 0.43 | 5, 5, 5, 4 | Poster | Reject | ✔ |

2587 | Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition | 4.67 | 0.47 | 4, 5, 5 | Poster | Poster | |

2588 | SSMF: Shifting Seasonal Matrix Factorization | 4.67 | 0.47 | 5, 4, 5 | Poster | Reject | ✔ |

2589 | CBP: backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method | 4.67 | 0.94 | 6, 4, 4 | Poster | Reject | ✔ |

2590 | Robust Counterfactual Explanations on Graph Neural Networks | 4.67 | 1.25 | 6, 3, 5 | Poster | Reject | ✔ |

2591 | On learning sparse vectors from mixture of responses | 4.60 | 0.49 | 5, 5, 4, 4, 5 | Poster | Reject | ✔ |

2592 | Adversarial Feature Desensitization | 4.50 | 1.12 | 6, 3, 4, 5 | Poster | Reject | ✔ |

2593 | Learning Student-Friendly Teacher Networks for Knowledge Distillation | 4.50 | 0.50 | 4, 4, 5, 5 | Poster | Reject | ✔ |

2594 | Adaptive Denoising via GainTuning | 4.50 | 0.50 | 5, 4, 4, 5 | Poster | Reject | ✔ |

2595 | Adversarial Attacks on Graph Classifiers via Bayesian Optimisation | 4.50 | 1.50 | 6, 5, 2, 5 | Poster | Reject | ✔ |

2596 | Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time | 4.50 | 0.50 | 5, 4, 4, 5 | Poster | Reject | ✔ |

2597 | Improved Regularization and Robustness for Fine-tuning in Neural Networks | 4.50 | 0.50 | 5, 4, 4, 5 | Poster | Reject | ✔ |

2598 | DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples | 4.50 | 0.50 | 4, 4, 5, 5 | Poster | Reject | ✔ |

2599 | Compressed Video Contrastive Learning | 4.50 | 0.50 | 5, 5, 4, 4 | Poster | Reject | ✔ |

2600 | Sample Selection for Fair and Robust Training | 4.50 | 0.50 | 5, 4, 4, 5 | Poster | Reject | ✔ |

2601 | One Explanation is Not Enough: Structured Attention Graphs for Image Classification | 4.50 | 0.50 | 4, 5, 5, 4 | Poster | Reject | ✔ |

2602 | Neural Tangent Kernel Maximum Mean Discrepancy | 4.50 | 1.50 | 7, 4, 4, 3 | Poster | Reject | ✔ |

2603 | Zero Time Waste: Recycling Predictions in Early Exit Neural Networks | 4.50 | 0.87 | 6, 4, 4, 4 | Poster | Reject | ✔ |

2604 | Uncertainty-Driven Loss for Single Image Super-Resolution | 4.50 | 0.50 | 4, 4, 5, 5 | Poster | Reject | ✔ |

2605 | Video Instance Segmentation using Inter-Frame Communication Transformers | 4.50 | 0.87 | 5, 5, 3, 5 | Poster | Reject | ✔ |

2606 | SNIPS: Solving Noisy Inverse Problems Stochastically | 4.50 | 0.50 | 4, 4, 5, 5 | Poster | Reject | ✔ |

2607 | Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation | 4.40 | 0.49 | 5, 4, 5, 4, 4 | Poster | Reject | ✔ |

2608 | Charting and Navigating the Space of Solutions for Recurrent Neural Networks | 4.33 | 0.47 | 5, 4, 4 | Poster | Reject | ✔ |

2609 | Learning Graph Models for Retrosynthesis Prediction | 4.33 | 0.47 | 4, 5, 4 | Poster | Reject | ✔ |

2610 | Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization | 4.33 | 1.11 | 3, 3, 4, 6, 5, 5 | Poster | Reject | ✔ |

2611 | On the Role of Optimization in Double Descent: A Least Squares Study | 4.33 | 0.47 | 5, 4, 4 | Poster | Reject | ✔ |

2612 | A Non-commutative Extension of Lee-Seung's Algorithm for Positive Semidefinite Factorizations | 4.33 | 0.47 | 4, 5, 4 | Poster | Reject | ✔ |

2613 | Efficient Statistical Assessment of Neural Network Corruption Robustness | 4.33 | 0.94 | 5, 3, 5 | Poster | Reject | ✔ |

2614 | α
-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression | 4.33 | 0.47 | 4, 5, 4 | Poster | Reject | ✔ |

2615 | Aligned Structured Sparsity Learning for Efficient Image Super-Resolution | 4.33 | 0.47 | 4, 4, 5 | Spotlight | Reject | ✔ |

2616 | Learning Generalized Gumbel-max Causal Mechanisms | 4.33 | 0.94 | 5, 5, 3 | Spotlight | Reject | ✔ |

2617 | Neural Routing by Memory | 4.25 | 1.09 | 4, 3, 6, 4 | Poster | Reject | ✔ |

2618 | Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks | 4.25 | 0.43 | 5, 4, 4, 4 | Poster | Reject | ✔ |

2619 | Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning | 4.25 | 0.83 | 5, 3, 4, 5 | Poster | Reject | ✔ |

2620 | Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models | 4.25 | 1.92 | 2, 5, 3, 7 | Poster | Reject | ✔ |

2621 | Asymptotically Best Causal Effect Identification with Multi-Armed Bandits | 4.25 | 0.83 | 5, 5, 4, 3 | Poster | Reject | ✔ |

2622 | EditGAN: High-Precision Semantic Image Editing | 4.25 | 0.83 | 5, 5, 3, 4 | Poster | Reject | ✔ |

2623 | STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data | 4.25 | 1.30 | 6, 3, 5, 3 | Poster | Reject | ✔ |

2624 | CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction | 4.25 | 0.83 | 5, 5, 3, 4 | Poster | Reject | ✔ |

2625 | Weak-shot Fine-grained Classification via Similarity Transfer | 4.25 | 0.83 | 3, 5, 5, 4 | Poster | Reject | ✔ |

2626 | Multi-Objective Meta Learning | 4.00 | 0.71 | 3, 4, 4, 5 | Poster | Reject | ✔ |

2627 | A Stochastic Newton Algorithm for Distributed Convex Optimization | 4.00 | 1.22 | 3, 4, 6, 3 | Poster | Reject | ✔ |

2628 | Edge Representation Learning with Hypergraphs | 4.00 | 0.00 | 4, 4, 4, 4 | Poster | Reject | ✔ |

2629 | Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | 4.00 | 0.71 | 4, 4, 3, 5 | Poster | Reject | ✔ |

2630 | Linear-Time Probabilistic Solution of Boundary Value Problems | 4.00 | 0.00 | 4, 4, 4 | Poster | Reject | ✔ |

2631 | Class-agnostic Reconstruction of Dynamic Objects from Videos | 3.75 | 0.43 | 4, 3, 4, 4 | Poster | Reject | ✔ |

2632 | CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum | 3.75 | 0.43 | 4, 4, 3, 4 | Poster | Reject | ✔ |