ICLR 2022 Statistics
Github
# (1095) Title R1 R2 ฮ”R Ratings ๐Ÿ‘
1 Bootstrapped Meta-Learning8.009.001.00
8, 8, 8, 8
8, 10, 8, 10
Oral
2 Towards a Unified View of Parameter-Efficient Transfer Learning8.008.670.67
6, 8, 10
8, 8, 10
Spotlight
3 Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space7.008.671.67
10, 6, 5
10, 8, 8
Oral
4 A Fine-Grained Analysis on Distribution Shift6.678.672.00
6, 8, 6
8, 10, 8
Oral
5 Self-Supervision Enhanced Feature Selection with Correlated Gates8.008.670.67
8, 8, 8
8, 8, 10
Spotlight
6 Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme7.678.671.00
10, 8, 5
10, 8, 8
Oral
7 What Happens after SGD Reaches Zero Loss? --A Mathematical Framework8.008.500.50
10, 8, 6, 8
10, 8, 8, 8
Spotlight
8 Score-Based Generative Modeling with Critically-Damped Langevin Diffusion8.008.500.50
8, 10, 8, 6
8, 10, 8, 8
Spotlight
9 Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation6.008.502.50
6, 5, 3, 10
8, 8, 8, 10
Spotlight
10 Expressiveness and Approximation Properties of Graph Neural Networks7.008.501.50
6, 6, 8, 8
8, 8, 8, 10
Oral
11 DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS7.258.501.25
8, 5, 8, 8
8, 8, 10, 8
Oral
12 Understanding over-squashing and bottlenecks on graphs via curvature7.008.501.50
8, 8, 6, 6
8, 10, 8, 8
Oral
13 Scaling Laws for Neural Machine Translation7.508.501.00
6, 10, 6, 8
8, 10, 8, 8
Spotlight
14 Neural Structured Prediction for Inductive Node Classification7.258.501.25
6, 10, 5, 8
8, 10, 8, 8
Oral
15 Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks6.008.002.00
8, 5, 5, 6
8, 8, 8, 8
Spotlight
16 EViT: Expediting Vision Transformers via Token Reorganizations7.008.001.00
6, 6, 8, 8
8, 8, 8, 8
Spotlight
17 Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics6.258.001.75
6, 6, 5, 8
8, 8, 8, 8
Oral
18 Comparing Distributions by Measuring Differences that Affect Decision Making8.008.000.00
8, 8, 8
8, 8, 8
Oral
19 Programmatic Reinforcement Learning without Oracles6.338.001.67
5, 8, 6
8, 8, 8
Spotlight
20 AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning7.508.000.50
8, 6, 8, 8
8, 8, 8, 8
Spotlight
21 Data-Efficient Graph Grammar Learning for Molecular Generation7.508.000.50
8, 6, 8, 8
8, 8, 8, 8
Oral
22 Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design8.008.000.00
8, 8, 8
8, 8, 8
Spotlight
23 Fast Regression for Structured Inputs5.678.002.33
6, 5, 6
10, 6, 8
Poster
24 Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization7.338.000.67
8, 8, 6
8, 8, 8
Oral
25 Efficiently Modeling Long Sequences with Structured State Spaces8.008.000.00
8, 8, 8
8, 8, 8
Oral
26 Assessing Generalization of SGD via Disagreement8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Spotlight
27 Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking6.008.002.00
5, 5, 8
8, 8, 8
Spotlight
28 Spike-inspired rank coding for fast and accurate recurrent neural networks6.338.001.67
6, 5, 8
8, 8, 8
Spotlight
29 MT3: Multi-Task Multitrack Music Transcription8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Spotlight
30 Hyperparameter Tuning with Renyi Differential Privacy7.008.001.00
8, 6, 6, 8
10, 8, 6, 8
Oral
31 MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling8.008.000.00
8, 8, 8
8, 8, 8
Oral
32 Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling7.008.001.00
8, 8, 5
8, 8, 8
Oral
33 Vision-Based Manipulators Need to Also See from Their Hands7.338.000.67
8, 6, 8
8, 8, 8
Oral
34 Meta-Learning with Fewer Tasks through Task Interpolation7.008.001.00
6, 8, 8, 5, 8
8, 8, 8, 8, 8
Oral
35 Finetuned Language Models are Zero-Shot Learners8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Oral
36 The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design6.608.001.40
8, 8, 5, 6, 6
8, 8, 8, 8, 8
Spotlight
37 Granger causal inference on DAGs identifies genomic loci regulating transcription6.758.001.25
8, 6, 5, 8
8, 8, 8, 8
Poster
38 iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data7.338.000.67
6, 8, 8
8, 8, 8
Oral
39 Possibility Before Utility: Learning And Using Hierarchical Affordances8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Spotlight
40 PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method7.008.001.00
8, 6, 8, 6
8, 8, 8, 8
Poster
41 Path Auxiliary Proposal for MCMC in Discrete Space5.258.002.75
8, 6, 6, 1
8, 8, 8, 8
Spotlight
42 Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design6.758.001.25
6, 8, 5, 8
8, 8, 8, 8
Oral
43 TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting8.008.000.00
8, 8
8, 8, 8
Spotlight
44 Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective6.678.001.33
6, 8, 6
8, 8, 8
Spotlight
45 Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks6.008.002.00
6, 6, 6
8, 8, 8
Oral
46 Adaptive Control Flow in Transformers Improves Systematic Generalization6.678.001.33
6, 8, 6
8, 8, 8
Poster
47 Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond8.008.000.00
8, 8, 8
8, 8, 8
Oral
48 Scalable Sampling for Nonsymmetric Determinantal Point Processes7.508.000.50
8, 6, 8, 8
8, 8, 8, 8
Spotlight
49 Frame Averaging for Invariant and Equivariant Network Design6.008.002.00
5, 5, 8
8, 8, 8, 8
Oral
50 Contrastive Label Disambiguation for Partial Label Learning8.008.000.00
8, 8, 8
8, 8, 8
Oral
51 Sampling with Mirrored Stein Operators8.008.000.00
8, 10, 6, 8
8, 10, 6, 8
Spotlight
52 Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory8.008.000.00
8, 8, 8
8, 8, 8
Spotlight
53 DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations7.338.000.67
8, 8, 6
8, 8, 8
Poster
54 RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation8.008.000.00
8, 8, 8
8, 8, 8
Oral
55 Learning transferable motor skills with hierarchical latent mixture policies6.508.001.50
6, 8, 6, 6
8, 8, 8, 8
Spotlight
56 SphereFace2: Binary Classification is All You Need for Deep Face Recognition7.008.001.00
8, 8, 5
8, 8, 8
Spotlight
57 Evaluating Distributional Distortion in Neural Language Modeling6.338.001.67
6, 5, 8
8, 8, 8
Poster
58 A General Analysis of Example-Selection for Stochastic Gradient Descent8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Spotlight
59 The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Oral
60 Real-Time Neural Voice Camouflage6.008.002.00
5, 5, 8
8, 8, 8
Oral
61 Natural Language Descriptions of Deep Features8.008.000.00
8, 8, 8
8, 8, 8
Oral
62 Rethinking the Representational Continuity: Towards Unsupervised Continual Learning6.758.001.25
5, 8, 6, 8
8, 8, 8, 8
Oral
63 Explanations of Black-Box Models based on Directional Feature Interactions6.508.001.50
6, 8, 6, 6
8, 8, 8, 8
Spotlight
64 EntQA: Entity Linking as Question Answering8.008.000.00
8, 8, 8
8, 8, 8
Spotlight
65 Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing7.008.001.00
8, 6, 8, 6
10, 8, 8, 6
Spotlight
66 NeuPL: Neural Population Learning6.508.001.50
6, 8, 6, 6
8, 8, 8, 8
Poster
67 Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream6.758.001.25
6, 5, 8, 8
8, 8, 8, 8
Spotlight
68 RelaxLoss: Defending Membership Inference Attacks without Losing Utility7.338.000.67
8, 8, 6
8, 8, 8
Spotlight
69 Language modeling via stochastic processes7.008.001.00
6, 6, 8, 8
8, 8, 8, 8
Oral
70 Fine-Tuning Distorts Pretrained Features and Underperforms Out-of-Distribution6.258.001.75
5, 6, 6, 8
8, 8, 8, 8
Oral
71 Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions7.338.000.67
8, 6, 8
8, 8, 8
Spotlight
72 Tackling the Generative Learning Trilemma with Denoising Diffusion GANs7.508.000.50
8, 6, 8, 8
8, 8, 8, 8
Spotlight
73 Universal Approximation Under Constraints is Possible with Transformers7.008.001.00
10, 3, 8
10, 6, 8
Spotlight
74 Learning Strides in Convolutional Neural Networks6.758.001.25
6, 8, 8, 5
8, 8, 8, 8
Spotlight
75 Progressive Distillation for Fast Sampling of Diffusion Models7.008.001.00
6, 6, 8, 8
8, 8, 8, 8
Spotlight
76 Convergent Graph Solvers7.008.001.00
8, 8, 6, 6
8, 8, 8, 8
Poster
77 The Information Geometry of Unsupervised Reinforcement Learning7.008.001.00
8, 8, 5
8, 8, 8
Oral
78 Poisoning and Backdooring Contrastive Learning6.758.001.25
8, 6, 8, 5
8, 8, 8, 8
Oral
79 Neural Deep Equilibrium Solvers8.008.000.00
8, 8, 8
8, 8, 8
Poster
80 Inductive Relation Prediction Using Analogy Subgraph Embeddings5.808.002.20
6, 5, 6, 6, 6
8, 8, 8, 8, 8
Poster
81 Probabilistic Implicit Scene Completion6.808.001.20
6, 6, 8, 8, 6
8, 8, 8, 8, 8
Spotlight
82 Perceiver IO: A General Architecture for Structured Inputs & Outputs7.508.000.50
8, 8, 6, 8
8, 8, 8, 8
Spotlight
83 Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models7.608.000.40
8, 6, 8, 8, 8
8, 8, 8, 8, 8
Oral
84 How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective6.508.001.50
6, 6, 8, 6
8, 8, 8, 8
Spotlight
85 Emergent Communication at Scale8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Spotlight
86 RotoGrad: Gradient Homogenization in Multitask Learning7.508.000.50
8, 6, 8, 8
8, 8, 8, 8
Spotlight
87 Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Spotlight
88 BEiT: BERT Pre-Training of Image Transformers7.508.000.50
6, 8, 8, 8
8, 8, 8, 8
Oral
89 Meta Discovery: Learning to Discover Novel Classes given Very Limited Data7.508.000.50
8, 8, 8, 6
8, 8, 8, 8
Spotlight
90 GNN-LM: Language Modeling based on Global Contexts via GNN7.678.000.33
5, 10, 8
6, 10, 8
Spotlight
91 Fast Differentiable Matrix Square Root6.338.001.67
5, 8, 6
8, 8, 8
Poster
92 On the Connection between Local Attention and Dynamic Depth-wise Convolution7.338.000.67
8, 6, 8
8, 8, 8
Spotlight
93 Visual Representation Learning Does Not Generalize Strongly Within the Same Domain6.758.001.25
6, 8, 8, 5
8, 8, 8, 8
Poster
94 A New Perspective on 'How Graph Neural Networks Go Beyond Weisfeiler-Lehman?'8.008.000.00
8, 8, 8, 8
8, 8, 8, 8
Oral
95 SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models6.008.002.00
5, 5, 8
8, 8, 8
Spotlight
96 On the Optimal Memorization Power of ReLU Neural Networks8.008.000.00
8, 8, 8
8, 8, 8
Spotlight
97 Task Relatedness-Based Generalization Bounds for Meta Learning7.508.000.50
8, 8, 8, 6
8, 8, 8, 8
Spotlight
98 Understanding Domain Randomization for Sim-to-real Transfer7.257.750.50
10, 8, 3, 8
10, 8, 5, 8
Spotlight
99 Planning in Stochastic Environments with a Learned Model7.007.750.75
10, 5, 5, 8
10, 8, 5, 8
Spotlight
100 Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration6.607.601.00
8, 6, 5, 6, 8
8, 8, 6, 8, 8
Spotlight
101 Local Feature Swapping for Generalization in Reinforcement Learning5.007.602.60
5, 3, 6, 5, 6
8, 6, 8, 8, 8
Poster
102 QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization6.007.501.50
6, 5, 5, 8
8, 8, 6, 8
Poster
103 Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations5.507.502.00
6, 8, 5, 3
8, 8, 6, 8
Poster
104 Optimization and Adaptive Generalization of Three layer Neural Networks7.257.500.25
8, 8, 8, 5
8, 8, 8, 6
Poster
105 Label Encoding for Regression Networks5.507.502.00
5, 6, 5, 6
8, 6, 8, 8
Spotlight
106 On the Importance of Firth Bias Reduction in Few-Shot Classification7.007.500.50
6, 8, 8, 6
6, 8, 8, 8
Spotlight
107 Approximation and Learning with Deep Convolutional Models: a Kernel Perspective7.507.500.00
8, 6, 8, 8
8, 6, 8, 8
Poster
108 Case-based Reasoning for Better Generalization in Text-Adventure Games5.757.501.75
5, 6, 6, 6
6, 8, 8, 8
Poster
109 Conditional Image Generation by Conditioning Variational Auto-Encoders6.007.501.50
8, 6, 5, 5
8, 8, 6, 8
Poster
110 DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools6.337.501.17
5, 6, 8
6, 6, 10, 8
Poster
111 When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?8.007.50-0.50
8, 8, 8
8, 8, 8, 6
Poster
112 The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models6.757.500.75
5, 8, 8, 6
6, 8, 8, 8
Poster
113 Accelerated Policy Learning with Parallel Differentiable Simulation6.007.501.50
6, 5, 5, 8
8, 8, 6, 8
Poster
114 NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy7.507.500.00
8, 8, 6, 8
8, 8, 6, 8
Poster
115 Know Your Action Set: Learning Action Relations for Reinforcement Learning5.257.502.25
5, 5, 6, 5
8, 6, 8, 8
Poster
116 LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations7.257.500.25
8, 5, 8, 8
8, 6, 8, 8
Poster
117 Understanding the Role of Self Attention for Efficient Speech Recognition6.757.500.75
6, 8, 5, 8
8, 8, 6, 8
Spotlight
118 StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis7.507.500.00
8, 6, 6, 10
8, 6, 6, 10
Poster
119 Extending the WILDS Benchmark for Unsupervised Adaptation7.007.500.50
8, 6, 6, 8
8, 8, 6, 8
Oral
120 Environment Predictive Coding for Visual Navigation6.257.501.25
6, 6, 5, 8
8, 6, 8, 8
Poster
121 Unsupervised Federated Learning is Possible7.007.500.50
8, 6, 6, 8
8, 6, 8, 8
Poster
122 Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction5.507.502.00
6, 5, 5, 6
8, 6, 8, 8
Spotlight
123 Deconstructing the Inductive Biases of Hamiltonian Neural Networks7.507.500.00
8, 8, 8, 6
8, 8, 8, 6
Spotlight
124 Learning more skills through optimistic exploration7.257.500.25
5, 8, 8, 8
6, 8, 8, 8
Spotlight
125 Large Language Models Can Be Strong Differentially Private Learners6.507.501.00
5, 5, 8, 8
8, 6, 8, 8
Oral
126 Meta-Imitation Learning by Watching Video Demonstrations5.257.502.25
5, 5, 5, 6
6, 8, 8, 8
Poster
127 Hybrid Local SGD for Federated Learning with Heterogeneous Communications5.757.501.75
6, 8, 3, 6
8, 8, 6, 8
Spotlight
128 Training invariances and the low-rank phenomenon: beyond linear networks6.757.500.75
5, 6, 8, 8
8, 6, 8, 8
Spotlight
129 CycleMLP: A MLP-like Architecture for Dense Prediction6.757.500.75
8, 5, 8, 6
8, 6, 8, 8
Oral
130 Continuous-Time Meta-Learning with Forward Mode Differentiation7.007.500.50
6, 8, 6, 8
8, 8, 6, 8
Spotlight
131 Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models7.007.500.50
6, 8, 8, 6
8, 8, 8, 6
Spotlight
132 Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception7.507.500.00
6, 8, 8, 8
6, 8, 8, 8
Poster
133 Can an Image Classifier Suffice For Action Recognition?7.257.500.25
8, 5, 8, 8
8, 6, 8, 8
Poster
134 Generative Models as a Data Source for Multiview Representation Learning6.257.501.25
3, 8, 6, 8
6, 8, 8, 8
Poster
135 CrossBeam: Learning to Search in Bottom-Up Program Synthesis7.007.500.50
6, 6, 8, 8
8, 6, 8, 8
Poster
136 Continual Learning with Filter Atom Swapping7.007.500.50
6, 8, 6, 8
8, 8, 6, 8
Spotlight
137 Information Prioritization through Empowerment in Visual Model-based RL5.507.502.00
3, 6, 5, 8
6, 8, 8, 8
Poster
138 Revisiting flow generative models for Out-of-distribution detection5.757.501.75
6, 6, 6, 5
8, 6, 8, 8
Poster
139 HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation6.757.500.75
8, 5, 8, 6
8, 6, 8, 8
Poster
140 Mention Memory: incorporating textual knowledge into Transformers through entity mention attention6.507.501.00
6, 6, 6, 8
6, 8, 8, 8
Poster
141 Coordination Among Neural Modules Through a Shared Global Workspace7.507.500.00
10, 8, 6, 6
10, 8, 6, 6
Oral
142 Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers7.007.500.50
8, 8, 6, 6
8, 8, 6, 8
Spotlight
143 Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks7.507.500.00
8, 8, 8, 6
8, 8, 8, 6
Spotlight
144 Vitruvion: A Generative Model of Parametric CAD Sketches6.257.501.25
8, 8, 3, 6
8, 8, 6, 8
Poster
145 Weighted Training for Cross-Task Learning7.507.500.00
8, 6, 8, 8
8, 6, 8, 8
Oral
146 No One Representation to Rule Them All: Overlapping Features of Training Methods7.007.500.50
6, 8, 6, 8
6, 8, 8, 8
Poster
147 UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning7.507.500.00
8, 6, 8, 8
8, 6, 8, 8
Poster
148 Relating transformers to models and neural representations of the hippocampal formation5.757.501.75
6, 3, 6, 8
8, 6, 8, 8
Poster
149 Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness8.007.50-0.50
8, 8, 8
8, 8, 8, 6
Spotlight
150 Interpretable Unsupervised Diversity Denoising and Artefact Removal7.257.500.25
5, 8, 8, 8
6, 8, 8, 8
Spotlight
151 ฯ€BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization6.257.501.25
6, 8, 5, 6
8, 8, 6, 8
Poster
152 TAPEX: Table Pre-training via Learning a Neural SQL Executor8.007.50-0.50
8, 8, 8
8, 8, 8, 6
Poster
153 On the Pitfalls of Analyzing Individual Neurons in Language Models6.757.500.75
5, 8, 8, 6
8, 8, 8, 6
Poster
154 Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies6.507.501.00
8, 5, 5, 8
8, 8, 6, 8
Poster
155 Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy5.257.502.25
3, 6, 6, 6
8, 8, 6, 8
Spotlight
156 Creating Training Sets via Weak Indirect Supervision6.257.501.25
6, 6, 5, 8
8, 8, 6, 8
Poster
157 Decoupled Adaptation for Cross-Domain Object Detection6.757.500.75
6, 8, 8, 5
8, 8, 8, 6
Poster
158 InfinityGAN: Towards Infinite-Pixel Image Synthesis7.257.500.25
5, 8, 8, 8
6, 8, 8, 8
Poster
159 Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation5.507.502.00
6, 5, 5, 6
8, 8, 6, 8
Spotlight
160 StyleAlign: Analysis and Applications of Aligned StyleGAN Models7.507.500.00
8, 6, 8, 8
8, 6, 8, 8
Oral
161 Imbedding Deep Neural Networks7.007.500.50
8, 8, 6, 6
8, 8, 8, 6
Spotlight
162 Sparse Communication via Mixed Distributions7.257.500.25
5, 8, 8, 8
6, 8, 8, 8
Oral
163 Constrained Policy Optimization via Bayesian World Models6.757.500.75
8, 8, 3, 8
8, 8, 6, 8
Spotlight
164 Deep Attentive Variational Inference5.757.501.75
6, 5, 6, 6
6, 8, 8, 8
Poster
165 Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent6.507.501.00
5, 8, 8, 5
6, 8, 8, 8
Poster
166 On Improving Adversarial Transferability of Vision Transformers6.007.501.50
6, 6, 6, 6
8, 8, 8, 6
Spotlight
167 Efficient Sharpness-aware Minimization for Improved Training of Neural Networks6.507.501.00
6, 6, 6, 8
8, 6, 8, 8
Poster
168 Learning Super-Features for Image Retrieval7.257.500.25
8, 8, 5, 8
8, 8, 6, 8
Poster
169 VAE Approximation Error: ELBO and Exponential Families7.007.500.50
8, 6, 8, 6
8, 8, 8, 6
Spotlight
170 Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond7.007.500.50
5, 10, 5, 8
6, 10, 6, 8
Spotlight
171 How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data7.507.500.00
6, 8, 8, 8
6, 8, 8, 8
Poster
172 Omni-Dimensional Dynamic Convolution7.007.500.50
6, 6, 8, 8
8, 6, 8, 8
Spotlight
173 Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning6.257.501.25
8, 8, 3, 6
8, 8, 6, 8
Spotlight
174 SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning6.257.501.25
5, 6, 8, 6
6, 8, 8, 8
Spotlight
175 Adversarial Robustness Through the Lens of Causality6.257.501.25
8, 6, 3, 8
8, 8, 6, 8
Poster
176 A Deep Variational Approach to Clustering Survival Data7.257.500.25
5, 8, 8, 8
6, 8, 8, 8
Poster
177 Denoising Likelihood Score Matching for Conditional Score-based Data Generation6.757.500.75
8, 5, 8, 6
8, 6, 8, 8
Poster
178 DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting7.507.500.00
8, 8, 8, 6
8, 8, 8, 6
Spotlight
179 CKConv: Continuous Kernel Convolution For Sequential Data6.507.501.00
6, 6, 8, 6
6, 8, 8, 8
Poster
180 Exploring the Limits of Large Scale Pre-training7.507.500.00
8, 8, 6, 8
8, 8, 6, 8
Spotlight
181 Whatโ€™s Wrong with Deep Learning in Tree Search for Combinatorial Optimization6.007.501.50
5, 6, 5, 8
8, 8, 6, 8
Poster
182 Strength of Minibatch Noise in SGD7.507.500.00
8, 8, 8, 6
8, 8, 8, 6
Spotlight
183 PAC-Bayes Information Bottleneck7.507.500.00
6, 8, 10, 6
6, 8, 10, 6
Spotlight
184 Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation6.757.500.75
6, 5, 8, 8
8, 6, 8, 8
Poster
185 Policy improvement by planning with Gumbel6.257.501.25
6, 5, 6, 8
8, 8, 6, 8
Spotlight
186 You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction5.607.401.80
6, 6, 6, 5, 5
8, 10, 6, 8, 5
Poster
187 Improving Mutual Information Estimation with Annealed and Energy-Based Bounds7.337.330.00
8, 6, 8
8, 6, 8
Poster
188 Controlling Directions Orthogonal to a Classifier6.677.330.67
6, 8, 6
8, 8, 6
Spotlight
189 Distribution Compression in Near-Linear Time6.677.330.67
6, 8, 6
6, 8, 8
Poster
190 Autoregressive Quantile Flows for Predictive Uncertainty Estimation7.007.330.33
5, 8, 8
6, 8, 8
Spotlight
191 Learning Causal Relationships from Conditional Moment Restrictions by Importance Weighting6.677.330.67
6, 8, 6
8, 8, 6
Spotlight
192 Domino: Discovering Systematic Errors with Cross-Modal Embeddings5.677.331.67
5, 6, 6
6, 8, 8
Oral
193 Distributional Decision Transformer for Hindsight Information Matching4.007.333.33
3, 5
8, 8, 6
Spotlight
194 Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness7.007.330.33
8, 8, 5
8, 8, 6
Poster
195 Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates6.007.331.33
5, 3, 10
6, 6, 10
Poster
196 GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation6.677.330.67
8, 6, 6
8, 8, 6
Oral
197 Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics6.337.331.00
6, 8, 5
8, 8, 6
Spotlight
198 ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity7.007.330.33
5, 8, 8
6, 8, 8
Poster
199 Superclass-Conditional Gaussian Mixture Model For Learning Fine-Grained Embeddings6.677.330.67
6, 6, 8
6, 8, 8
Spotlight
200 Label-Efficient Semantic Segmentation with Diffusion Models5.007.332.33
3, 6, 6
8, 8, 6
Poster
201 Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future7.007.330.33
6, 8
6, 8, 8
Poster
202 Open-Set Recognition: A Good Closed-Set Classifier is All You Need6.677.330.67
8, 6, 6
8, 6, 8
Oral
203 Compositional Training for End-to-End Deep AUC Maximization7.337.330.00
8, 8, 6
8, 8, 6
Spotlight
204 Open-vocabulary Object Detection via Vision and Language Knowledge Distillation7.007.330.33
8, 8, 5
8, 8, 6
Poster
205 Convergent and Efficient Deep Q Learning Algorithm5.337.332.00
5, 6, 5
6, 10, 6
Poster
206 Learning-Augmentedk-means Clustering6.007.331.33
6, 6, 6
6, 8, 8
Spotlight
207 Efficient Self-supervised Vision Transformers for Representation Learning6.677.330.67
6, 6, 8
8, 6, 8
Poster
208 Sound Adversarial Audio-Visual Navigation5.677.331.67
5, 6, 6
6, 8, 8
Poster
209 Actor-critic is implicitly biased towards high entropy optimal policies6.337.331.00
5, 8, 6
8, 8, 6
Poster
210 Boosting Randomized Smoothing with Variance Reduced Classifiers6.677.330.67
6, 8, 6
8, 8, 6
Spotlight
211 Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver6.337.331.00
6, 5, 8
8, 6, 8
Spotlight
212 Chunked Autoregressive GAN for Conditional Waveform Synthesis7.007.330.33
5, 8, 8
6, 8, 8
Poster
213 A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion7.007.330.33
5, 8, 8
6, 8, 8
Poster
214 IntSGD: Adaptive Floatless Compression of Stochastic Gradients6.677.330.67
6, 8, 6
6, 8, 8
Spotlight
215 Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models7.337.330.00
6, 8, 8
6, 8, 8
Spotlight
216 Training Structured Neural Networks Through Manifold Identification and Variance Reduction5.337.332.00
5, 6, 5
8, 8, 6
Poster
217 On the approximation properties of recurrent encoder-decoder architectures7.007.330.33
8, 8, 5
8, 8, 6
Spotlight
218 A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs6.337.331.00
5, 8, 6
6, 8, 8
Poster
219 Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis6.677.330.67
8, 6, 6
8, 6, 8
Poster
220 CoBERL: Contrastive BERT for Reinforcement Learning6.337.331.00
6, 5, 8
6, 8, 8
Spotlight
221 Hybrid Random Features5.007.332.33
6, 6, 3
8, 8, 6
Poster
222 Graphon based Clustering and Testing of Networks: Algorithms and Theory5.677.331.67
8, 3, 6
8, 6, 8
Poster
223 Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization6.677.330.67
6, 6, 8
8, 6, 8
Poster
224 Bregman Gradient Policy Optimization6.337.331.00
8, 3, 8
8, 6, 8
Poster
225 Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection6.337.331.00
8, 5, 6
8, 6, 8
Poster
226 Relational Surrogate Loss Learning7.337.330.00
8, 6, 8
8, 6, 8
Poster
227 Discovering Invariant Rationales for Graph Neural Networks6.337.331.00
6, 8, 5
8, 8, 6
Poster
228 Causal ImageNet: How to discover spurious features in Deep Learning?7.007.330.33
8, 5, 8
8, 6, 8
Poster
229 CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation5.677.331.67
3, 8, 6
6, 8, 8
Poster
230 ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics6.677.330.67
6, 8, 6
6, 8, 8
Oral
231 Fast topological clustering with Wasserstein distance5.337.332.00
5, 6, 5
8, 8, 6
Poster
232 Critical Points in Quantum Generative Models7.007.330.33
8, 5, 8
8, 6, 8
Poster
233 Delaunay Component Analysis for Evaluation of Data Representations7.007.330.33
6, 8
8, 8, 6
Poster
234 8-bit Optimizers via Block-wise Quantization6.337.331.00
6, 8, 5
6, 8, 8
Spotlight
235 An Experimental Design Perspective on Exploration in Reinforcement Learning5.757.251.50
6, 3, 6, 8
8, 5, 8, 8
Poster
236 Fixed Neural Network Steganography: Train the images, not the network6.257.251.00
6, 5, 8, 6
8, 5, 8, 8
Poster
237 On Predicting Generalization using GANs6.257.251.00
6, 5, 6, 8
8, 5, 8, 8
Spotlight
238 Self-supervised Learning is More Robust to Dataset Imbalance7.257.250.00
8, 5, 8, 8
8, 5, 8, 8
Spotlight
239 Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?6.007.251.25
5, 6, 8, 5
8, 8, 8, 5
Poster
240 Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization6.257.251.00
8, 5, 6, 6
8, 5, 8, 8
Poster
241 Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations6.757.250.50
3, 8, 6, 10
5, 8, 6, 10
Poster
242 On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications7.257.250.00
10, 6, 5, 8
10, 6, 5, 8
Poster
243 Learning Long-Term Reward Redistribution via Randomized Return Decomposition5.337.251.92
5, 5, 6
8, 5, 8, 8
Spotlight
244 How Do Vision Transformers Work?7.257.250.00
8, 5, 8, 8
8, 5, 8, 8
Spotlight
245 Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation6.757.250.50
8, 8, 8, 3
8, 10, 8, 3
Poster
246 Learning Optimal Conformal Classifiers6.507.250.75
5, 8, 5, 8
8, 8, 5, 8
Spotlight
247 Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems7.257.250.00
8, 8, 5, 8
8, 8, 5, 8
Spotlight
248 Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks5.677.251.58
5, 6, 6
10, 8, 6, 5
Poster
249 Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions6.257.251.00
6, 5, 8, 6
8, 5, 8, 8
Poster
250 Continual Learning with Recursive Gradient Optimization6.757.250.50
8, 5, 8, 6
8, 5, 8, 8
Spotlight
251 Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions5.757.251.50
6, 6, 6, 5
8, 8, 8, 5
Spotlight
252 CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability5.757.251.50
6, 5, 6, 6
8, 5, 8, 8
Poster
253 POETREE: Interpretable Policy Learning with Adaptive Decision Trees5.257.252.00
6, 3, 6, 6
8, 5, 8, 8
Spotlight
254 Differentiable Scaffolding Tree for Molecule Optimization7.257.250.00
6, 10, 8, 5
6, 10, 8, 5
Poster
255 Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters5.507.251.75
5, 6, 3, 8
8, 8, 5, 8
Spotlight
256 Transformer-based Transform Coding7.007.200.20
8, 5, 6, 8, 8
8, 6, 6, 8, 8
Poster
257 Dual Lottery Ticket Hypothesis5.007.202.20
6, 6, 5, 3
8, 8, 8, 6, 6
Poster
258 Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration6.007.201.20
6, 6, 5, 5, 8
8, 6, 6, 8, 8
Spotlight
259 Pix2seq: A Language Modeling Framework for Object Detection6.807.200.40
8, 6, 6, 6, 8
8, 6, 8, 6, 8
Poster
260 SGD Can Converge to Local Maxima6.607.200.60
8, 6, 8, 8, 3
8, 6, 8, 8, 6
Spotlight
261 Responsible Disclosure of Generative Models Using Scalable Fingerprinting6.407.200.80
8, 8, 3, 8, 5
8, 8, 6, 8, 6
Spotlight
262 Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions5.807.201.40
5, 6, 6, 6, 6
6, 8, 8, 8, 6
Spotlight
263 MetaMorph: Learning Universal Controllers with Transformers6.207.201.00
8, 8, 3, 6, 6
8, 8, 6, 6, 8
Poster
264 Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling4.007.203.20
3, 3, 6, 5, 3
6, 6, 8, 8, 8
Spotlight
265 SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training6.807.200.40
6, 6, 6, 8, 8
6, 6, 8, 8, 8
Poster
266 Contextualized Scene Imagination for Generative Commonsense Reasoning5.757.001.25
8, 6, 6, 3
8, 8, 6, 6
Poster
267 Phenomenology of Double Descent in Finite-Width Neural Networks5.207.001.80
3, 3, 6, 6, 8
3, 8, 8, 8, 8
Poster
268 Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality6.257.000.75
6, 8, 6, 5
6, 8, 6, 8
Poster
269 On Distributed Adaptive Optimization with Gradient Compression7.007.000.00
5, 8, 8
5, 8, 8
Poster
270 Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?6.257.000.75
8, 5, 6, 6
8, 6, 6, 8
Poster
271 Context-Aware Sparse Deep Coordination Graphs6.257.000.75
6, 5, 6, 8
8, 6, 6, 8
Spotlight
272 Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?6.257.000.75
3, 6, 8, 8
6, 6, 8, 8
Poster
273 Multi-Stage Episodic Control for Strategic Exploration in Text Games6.257.000.75
5, 8, 6, 6
6, 8, 6, 8
Spotlight
274 Leveraging unlabeled data to predict out-of-distribution performance6.207.000.80
6, 8, 6, 5, 6
6, 8, 8, 5, 8
Poster
275 Fortuitous Forgetting in Connectionist Networks6.007.001.00
6, 10, 5, 3
6, 10, 6, 6
Poster
276 A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning6.507.000.50
8, 8, 5, 5
8, 8, 6, 6
Poster
277 On Bridging Generic and Personalized Federated Learning for Image Classification5.677.001.33
6, 6, 5
8, 8, 5
Spotlight
278 Learning Transferable Reward for Query Object Localization with Policy Adaptation5.507.001.50
6, 5, 5, 6
8, 6, 6, 8
Poster
279 CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture6.257.000.75
5, 6, 6, 8
6, 8, 6, 8
Poster
280 Convergent Boosted Smoothing for Modeling GraphData with Tabular Node Features7.007.000.00
6, 6, 8, 8
6, 6, 8, 8
Spotlight
281 Revisiting Over-smoothing in BERT from the Perspective of Graph6.757.000.25
8, 8, 5, 6
8, 8, 6, 6
Spotlight
282 On the Uncomputability of Partition Functions in Energy-Based Sequence Models6.757.000.25
8, 6, 8, 5
8, 6, 8, 6
Spotlight
283 The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks5.757.001.25
6, 5, 6, 6
6, 6, 8, 8
Poster
284 Should I Run Offline Reinforcement Learning or Behavioral Cloning?5.507.001.50
8, 3, 8, 3
8, 6, 8, 6
Poster
285 Permutation-Based SGD: Is Random Optimal?7.007.000.00
6, 6, 6, 10
6, 6, 6, 10
Poster
286 Hindsight: Posterior-guided training of retrievers for improved open-ended generation6.257.000.75
6, 6, 5, 8
6, 8, 6, 8
Poster
287 Sample and Computation Redistribution for Efficient Face Detection7.337.00-0.33
6, 8, 8
6, 8, 8, 6
Poster
288 Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation5.677.001.33
5, 6, 6
6, 8, 6, 8
Spotlight
289 Chaos is a Ladder: A New Understanding of Contrastive Learning5.507.001.50
3, 8, 8, 3
6, 8, 8, 6
Poster
290 Rethinking Adversarial Transferability from a Data Distribution Perspective6.007.001.00
5, 8, 5
8, 8, 5
Poster
291 High Probability Generalization Bounds for Minimax Problems with Fast Rates6.257.000.75
5, 6, 6, 8
6, 8, 6, 8
Poster
292 Unsupervised Semantic Segmentation by Distilling Feature Correspondences6.757.000.25
5, 8, 6, 8
6, 8, 6, 8
Poster
293 Is High Variance Unavoidable in RL? A Case Study in Continuous Control5.507.001.50
6, 5, 6, 5
6, 6, 10, 6
Poster
294 C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks6.757.000.25
5, 8, 8, 6
6, 8, 8, 6
Poster
295 Variational methods for simulation-based inference5.507.001.50
6, 5, 6, 5
8, 6, 8, 6
Spotlight
296 Divisive Feature Normalization Improves Image Recognition Performance in AlexNet6.007.001.00
5, 6, 8, 5
6, 8, 8, 6
Poster
297 An Unconstrained Layer-Peeled Perspective on Neural Collapse6.507.000.50
8, 6, 6, 6
8, 8, 6, 6
Poster
298 Data-Driven Offline Optimization for Architecting Hardware Accelerators6.507.000.50
8, 6, 6, 6
8, 8, 6, 6
Poster
299 cosFormer: Rethinking Softmax In Attention6.257.000.75
6, 8, 3, 8
6, 8, 6, 8
Poster
300 Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning6.757.000.25
6, 5, 8, 8
6, 6, 8, 8
Spotlight
301 Value Gradient weighted Model-Based Reinforcement Learning6.007.001.00
6, 6, 6, 6
8, 6, 8, 6
Spotlight
302 Unsupervised Discovery of Object Radiance Fields6.337.000.67
8, 6, 5
8, 8, 5
Poster
303 MonoDistill: Learning Spatial Features for Monocular 3D Object Detection6.407.000.60
5, 6, 8, 5, 8
5, 8, 8, 6, 8
Poster
304 Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction7.007.000.00
8, 6, 8, 6
8, 6, 8, 6
Poster
305 Phase Collapse in Neural Networks5.757.001.25
3, 6, 8, 6
6, 6, 8, 8
Poster
306 Coherence-based Label Propagation over Time Series for Accelerated Active Learning7.007.000.00
6, 6, 6, 10
6, 6, 6, 10
Poster
307 Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space6.507.000.50
6, 6, 6, 8
6, 8, 6, 8
Poster
308 MCMC Should Mix: Learning Energy-Based Model with Flow-Based Backbone6.007.001.00
8, 5, 3, 8
8, 6, 6, 8
Poster
309 Spanning Tree-based Graph Generation for Molecules5.757.001.25
3, 8, 6, 6
8, 8, 6, 6
Spotlight
310 COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation5.507.001.50
5, 6
6, 8, 8, 6
Spotlight
311 Gradient Information Matters in Policy Optimization by Back-propagating through Model4.507.002.50
6, 5, 6, 1
8, 6, 8, 6
Poster
312 Multi-objective Optimization by Learning Space Partition6.757.000.25
6, 5, 8, 8
6, 6, 8, 8
Poster
313 Equivariant Subgraph Aggregation Networks6.257.000.75
3, 8, 8, 6
6, 8, 8, 6
Spotlight
314 Churn Reduction via Distillation7.007.000.00
8, 8, 5
8, 8, 5
Spotlight
315 Spherical Message Passing for 3D Molecular Graphs5.677.001.33
6, 6, 5
8, 8, 5
Poster
316 AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis5.757.001.25
6, 6, 6, 5
8, 8, 6, 6
Poster
317 Improved deterministic l2 robustness on CIFAR-10 and CIFAR-1006.257.000.75
8, 3, 6, 8
8, 6, 6, 8
Spotlight
318 When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations5.507.001.50
5, 8, 3, 6
5, 8, 8, 6, 8
Spotlight
319 PF-GNN: Differentiable particle filtering based approximation of universal graph representations6.257.000.75
6, 5, 6, 8
6, 8, 6, 8
Poster
320 LoRA: Low-Rank Adaptation of Large Language Models6.007.001.00
8, 5, 8, 3
8, 6, 8, 6
Poster
321 EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits6.257.000.75
8, 6, 6, 5
8, 8, 6, 6
Spotlight
322 Scarf: Self-Supervised Contrastive Learning using Random Feature Corruption6.257.000.75
8, 6, 6, 5
8, 8, 6, 6
Spotlight
323 Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners6.507.000.50
6, 6, 6, 8
8, 6, 6, 8
Poster
324 Bootstrapping Semantic Segmentation with Regional Contrast5.507.001.50
5, 3, 6, 8
6, 6, 8, 8
Poster
325 Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations6.007.001.00
5, 5, 6, 8
6, 6, 8, 8
Poster
326 Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching6.757.000.25
6, 8, 5, 8
6, 8, 6, 8
Poster
327 Message Passing Neural PDE Solvers6.257.000.75
8, 6, 3, 8
8, 6, 6, 8
Spotlight
328 Efficient Active Search for Combinatorial Optimization Problems7.007.000.00
6, 6, 8, 8
6, 6, 8, 8
Poster
329 Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting6.007.001.00
6, 5, 5, 8
8, 6, 6, 8
Oral
330 The MultiBERTs: BERT Reproductions for Robustness Analysis7.337.00-0.33
6, 8, 8
6, 8, 8, 6
Spotlight
331 Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning7.007.000.00
5, 8, 8
6, 8, 8, 6
Poster
332 Minimax Optimization with Smooth Algorithmic Adversaries7.007.000.00
6, 6, 8, 8
6, 6, 8, 8
Poster
333 Compositional Attention: Disentangling Search and Retrieval5.677.001.33
5, 6, 6
8, 6, 6, 8
Spotlight
334 When should agents explore?7.007.000.00
6, 8, 8, 6
6, 8, 8, 6
Spotlight
335 Domain Adversarial Training: A Game Perspective7.007.000.00
8, 6, 8, 6
8, 6, 8, 6
Poster
336 Contrastive Fine-grained Class Clustering via Generative Adversarial Networks6.257.000.75
5, 8, 6, 6
6, 8, 6, 8
Spotlight
337 Conditional Object-Centric Learning from Video6.507.000.50
8, 5, 8, 5
8, 6, 8, 6
Poster
338 Visual Correspondence Hallucination7.007.000.00
8, 5, 8
8, 5, 8
Poster
339 Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View6.257.000.75
8, 6, 5, 6
8, 8, 6, 6
Poster
340 NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning5.337.001.67
6, 5, 5
8, 5, 8
Spotlight
341 Geometric and Physical Quantities improve E(3) Equivariant Message Passing6.337.000.67
10, 6, 6, 6, 5, 5
10, 6, 8, 6, 6, 6
Spotlight
342 GreaseLM: Graph REASoning Enhanced Language Models6.007.001.00
6, 6, 6, 6
6, 6, 8, 8
Spotlight
343 Neural Relational Inference with Node-Specific Information6.337.000.67
8, 5, 6
8, 5, 8
Poster
344 D-CODE: Discovering Closed-form ODEs from Observed Trajectories6.507.000.50
6, 6, 6, 8
6, 8, 6, 8
Spotlight
345 Learned Simulators for Turbulence6.007.001.00
8, 5, 5, 6
8, 6, 6, 8
Poster
346 Active Hierarchical Exploration with Stable Subgoal Representation Learning6.257.000.75
8, 6, 6, 5
8, 6, 8, 6
Poster
347 On the Limitations of Multimodal VAEs6.257.000.75
6, 6, 5, 8
6, 8, 6, 8
Poster
348 Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling5.507.001.50
8, 5, 3, 6
8, 8, 6, 6
Poster
349 Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks6.757.000.25
6, 5, 8, 8
6, 6, 8, 8
Poster
350 Shuffle Private Stochastic Convex Optimization6.007.001.00
5, 8, 8, 3
6, 8, 8, 6
Poster
351 Self-Joint Supervised Learning7.007.000.00
8, 5, 8
8, 5, 8
Poster
352 SO(2)-Equivariant Reinforcement Learning6.607.000.40
5, 6, 6, 8, 8
5, 6, 8, 8, 8
Spotlight
353 Anomaly Detection for Tabular Data with Internal Contrastive Learning5.677.001.33
5, 6, 6
6, 8, 8, 6
Poster
354 On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning7.007.000.00
8, 5, 8
8, 5, 8
Spotlight
355 A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning5.757.001.25
5, 6, 6, 6
6, 8, 6, 8
Poster
356 Long Expressive Memory for Sequence Modeling6.257.000.75
6, 5, 6, 8
6, 6, 8, 8
Spotlight
357 Procedural generalization by planning with self-supervised world models6.757.000.25
6, 5, 8, 8
6, 6, 8, 8
Poster
358 Who Is Your Right Mixup Partner in Positive and Unlabeled Learning6.757.000.25
8, 5, 8, 6
8, 6, 8, 6
Poster
359 Ancestral protein sequence reconstruction using a tree-structured Ornstein-Uhlenbeck variational autoencoder6.007.001.00
8, 5, 5
8, 5, 8
Poster
360 Learning Towards The Largest Margins6.757.000.25
6, 8, 5, 8
6, 8, 6, 8
Poster
361 DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization5.757.001.25
8, 3, 6, 6
8, 6, 6, 8
Spotlight
362 Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series5.507.001.50
3, 6, 5, 8
6, 8, 6, 8
Spotlight
363 CURVATURE-GUIDED DYNAMIC SCALE NETWORKS FOR MULTI-VIEW STEREO5.007.002.00
6, 3, 8, 3
6, 8, 8, 6
Poster
364 Stochastic Training is Not Necessary for Generalization5.807.001.20
5, 3, 8, 8, 5
6, 5, 8, 10, 6
Poster
365 Sqrt(d) Dimension Dependence of Langevin Monte Carlo7.007.000.00
8, 6, 8, 6
8, 6, 8, 6
Poster
366 The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs6.507.000.50
8, 6, 6, 6
8, 6, 6, 8
Poster
367 GiraffeDet: A Heavy-Neck Paradigm for Object Detection6.007.001.00
5, 5, 8
8, 5, 8
Poster
368 Joint Shapley values: a measure of joint feature importance7.007.000.00
8, 8, 5
8, 8, 5
Poster
369 Deep ReLU Networks Preserve Expected Length6.257.000.75
8, 6, 3, 8
8, 6, 6, 8
Poster
370 Resolving Training Biases via Influence-based Data Relabeling5.757.001.25
3, 6, 8, 6
6, 6, 8, 8
Oral
371 Noisy Feature Mixup7.007.000.00
8, 6, 8, 6
8, 6, 8, 6
Poster
372 Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path6.007.001.00
8, 5, 6, 5
8, 8, 6, 6
Oral
373 Online Hyperparameter Meta-Learning with Hypergradient Distillation7.007.000.00
6, 8, 8, 6
6, 8, 8, 6
Spotlight
374 Learning Hierarchical Structures with Differentiable Nondeterministic Stacks6.757.000.25
8, 5, 8, 6
8, 6, 8, 6
Spotlight
375 Random matrices in service of ML footprint: ternary random features with no performance loss6.257.000.75
5, 6, 8, 6
6, 6, 8, 8
Poster
376 Distributionally Robust Models with Parametric Likelihood Ratios6.507.000.50
6, 6, 8, 6
8, 6, 8, 6
Poster
377 You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks6.257.000.75
5, 6, 6, 8
6, 8, 6, 8
Poster
378 NASPY: Automated Extraction of Automated Machine Learning Models7.007.000.00
6, 8, 8, 6
6, 8, 8, 6
Spotlight
379 A generalization of the randomized singular value decomposition6.337.000.67
5, 8, 6
5, 8, 8
Poster
380 Equivariant Transformers for Neural Network based Molecular Potentials6.257.000.75
8, 5, 6, 6
8, 6, 8, 6
Spotlight
381 Generalization of Overparametrized Deep Neural Network Under Noisy Observations6.257.000.75
6, 5, 8, 6
6, 6, 8, 8
Poster
382 Chemical-Reaction-Aware Molecule Representation Learning6.007.001.00
6, 6, 6, 6
6, 6, 8, 8
Poster
383 Offline Reinforcement Learning with Value-based Episodic Memory5.256.831.58
5, 6, 5, 5
6, 8, 6, 5, 8, 8
Poster
384 How Does SimSiam Avoid Collapse Without Negative Samples? Towards a Unified Understanding of Progress in SSL6.206.800.60
8, 5, 5, 5, 8
8, 6, 6, 6, 8
Poster
385 Tracking the risk of a deployed model and detecting harmful distribution shifts5.806.801.00
6, 6, 6, 5, 6
6, 8, 6, 6, 8
Poster
386 Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks6.606.800.20
8, 8, 6, 6, 5
8, 8, 6, 6, 6
Poster
387 Latent Image Animator: Learning to animate image via latent space navigation6.806.800.00
8, 6, 6, 6, 8
8, 6, 6, 6, 8
Poster
388 Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward5.606.801.20
6, 5, 6, 6, 5
6, 6, 8, 8, 6
Spotlight
389 On the Certified Robustness for Ensemble Models and Beyond6.206.800.60
5, 6, 6, 6, 8
6, 8, 6, 6, 8
Poster
390 Multi-Critic Actor Learning: Teaching RL Policies to Act with Style5.006.801.80
8, 3, 3, 6, 5
8, 6, 6, 8, 6
Poster
391 Revisiting Design Choices in Offline Model Based Reinforcement Learning5.406.801.40
8, 5, 6, 3, 5
8, 6, 8, 6, 6
Spotlight
392 Learning Altruistic Behaviours in Reinforcement Learning without External Rewards6.006.800.80
8, 6, 6, 5, 5
8, 6, 8, 6, 6
Spotlight
393 Learning to Generalize across Domains on Single Test Samples5.806.801.00
5, 5, 6, 5, 8
5, 8, 8, 5, 8
Poster
394 Reinforcement Learning in Presence of Discrete Markovian Context Evolution6.406.800.40
5, 6, 5, 8, 8
6, 6, 6, 8, 8
Poster
395 GNN is a Counter? Revisiting GNN for Question Answering6.256.750.50
6, 5, 6, 8
6, 5, 8, 8
Poster
396 Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently6.506.750.25
5, 8, 5, 8
5, 8, 6, 8
Poster
397 Pareto Policy Pool for Model-based Offline Reinforcement Learning5.256.751.50
5, 5, 5, 6
8, 6, 5, 8
Poster
398 Sparsity Winning Twice: Better Robust Generalization from More Efficient Training5.756.751.00
6, 6, 6, 5
6, 8, 8, 5
Poster
399 Deep AutoAugment5.506.751.25
3, 8, 8, 3
5, 8, 8, 6
Poster
400 BAM: Bayes Augmented with Memory6.506.750.25
5, 5, 8, 8
6, 5, 8, 8
Poster
401 Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect5.256.751.50
5, 5, 3, 8
8, 6, 5, 8
Poster
402 FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations6.256.750.50
6, 8, 8, 3
6, 8, 8, 5
Poster
403 On the Learning of Quasimetrics6.256.750.50
8, 6, 5, 6
8, 6, 5, 8
Poster
404 Synchromesh: Reliable Code Generation from Pre-trained Language Models6.256.750.50
6, 5, 8, 6
6, 5, 8, 8
Poster
405 Adversarial Support Alignment6.006.750.75
5, 3, 8, 8
8, 3, 8, 8
Spotlight
406 Learning Object-Oriented Dynamics for Planning from Text6.756.750.00
8, 8, 5, 6
8, 8, 5, 6
Poster
407 How to Train Your MAML to Excel in Few-Shot Classification6.256.750.50
8, 6, 8, 3
8, 8, 8, 3
Poster
408 A Fine-Tuning Approach to Belief State Modeling5.006.751.75
3, 8, 6, 3
8, 8, 8, 3
Poster
409 Path Integral Sampler: A Stochastic Control Approach For Sampling6.756.750.00
8, 8, 6, 5
8, 8, 6, 5
Poster
410 DIVA: Dataset Derivative of a Learning Task7.006.75-0.25
5, 8, 8
6, 8, 8, 5
Poster
411 A First-Occupancy Representation for Reinforcement Learning6.756.750.00
8, 8, 5, 6
8, 8, 5, 6
Poster
412 Towards Unknown-aware Learning with Virtual Outlier Synthesis5.756.751.00
6, 6, 6, 5
6, 8, 8, 5
Poster
413 Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design4.256.752.50
3, 8, 3, 3
3, 8, 8, 8
Spotlight
414 Improving Non-Autoregressive Translation Models Without Distillation6.256.750.50
3, 8, 8, 6
3, 8, 8, 8
Poster
415 Learning Neural Contextual Bandits through Perturbed Rewards5.756.751.00
6, 6, 5, 6
8, 8, 5, 6
Poster
416 Better Supervisory Signals by Observing Learning Paths4.756.752.00
3, 5, 5, 6
8, 5, 6, 8
Poster
417 Constrained Graph Mechanics Networks5.006.751.75
6, 6, 3, 5
6, 8, 5, 8
Poster
418 Dynamics-Aware Comparison of Learned Reward Functions6.006.750.75
8, 5, 6, 5
8, 5, 8, 6
Spotlight
419 Model-augmented Prioritized Experience Replay6.756.750.00
6, 8, 5, 8
6, 8, 5, 8
Poster
420 Enhancing Cross-lingual Transfer by Manifold Mixup5.756.751.00
6, 6, 5, 6
8, 6, 5, 8
Poster
421 Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension6.756.750.00
8, 6, 5, 8
8, 6, 5, 8
Spotlight
422 Knowledge Removal in Sampling-based Bayesian Inference6.756.750.00
8, 3, 8, 8
8, 3, 8, 8
Poster
423 Mapping Language Models to Grounded Conceptual Spaces6.756.750.00
5, 8, 8, 6
5, 8, 8, 6
Poster
424 A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training6.756.750.00
8, 5, 6, 8
8, 5, 6, 8
Poster
425 Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks5.336.751.42
5, 5, 6
8, 5, 8, 6
Poster
426 Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs6.006.750.75
5, 6, 8, 5
5, 8, 8, 6
Poster
427 Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games6.756.750.00
8, 5, 8, 6
8, 5, 8, 6
Poster
428 Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation5.756.751.00
8, 5, 5, 5
8, 6, 8, 5
Poster
429 SketchODE: Learning neural sketch representation in continuous time6.256.750.50
3, 8, 8, 6
5, 8, 8, 6
Poster
430 Sound and Complete Neural Network Repair with Minimality and Locality Guarantees6.006.750.75
5, 8, 3, 8
5, 8, 6, 8
Poster
431 Scene Transformer: A unified architecture for predicting future trajectories of multiple agents6.006.750.75
8, 3, 5, 8
8, 6, 5, 8
Poster
432 Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning6.756.750.00
8, 6, 8, 5
8, 6, 8, 5
Poster
433 ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning5.756.751.00
6, 6, 3, 8
8, 6, 5, 8
Poster
434 Likelihood Training of Schrรถdinger Bridge using Forward-Backward SDEs Theory5.256.751.50
3, 8, 5, 5
6, 8, 5, 8
Poster
435 Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields6.756.750.00
10, 6, 6, 5
10, 6, 6, 5
Poster
436 Unrolling PALM for Sparse Semi-Blind Source Separation4.256.752.50
6, 3, 3, 5
8, 8, 5, 6
Poster
437 Generalized rectifier wavelet covariance models for texture synthesis5.336.751.42
3, 8, 5
8, 8, 8, 3
Poster
438 Representation Learning for Online and Offline RL in Low-rank MDPs5.506.751.25
5, 6, 5, 6
8, 5, 6, 8
Spotlight
439 Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity6.756.750.00
6, 8, 5, 8
6, 8, 5, 8
Poster
440 Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting5.506.751.25
3, 3, 8, 8
5, 6, 8, 8
Poster
441 Leveraging Automated Unit Tests for Unsupervised Code Translation6.756.750.00
8, 8, 5, 6
8, 8, 5, 6
Spotlight
442 Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios6.506.750.25
8, 5, 5, 8
8, 6, 5, 8
Poster
443 Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning5.756.751.00
6, 6, 6, 5
8, 8, 6, 5
Poster
444 A Loss Curvature Perspective on Training Instabilities of Deep Learning Models6.756.750.00
6, 8, 8, 5
6, 8, 8, 5
Poster
445 Surreal-GAN:Semi-Supervised Representation Learning via GAN for uncovering heterogeneous disease-related imaging patterns6.006.750.75
5, 6, 5, 8
6, 8, 5, 8
Poster
446 Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game4.506.752.25
5, 3, 5, 5
8, 6, 8, 5
Poster
447 Adversarially Robust Conformal Prediction6.756.750.00
5, 8, 6, 8
5, 8, 6, 8
Poster
448 Topological Experience Replay5.506.751.25
6, 5, 8, 3
8, 6, 8, 5
Poster
449 Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations5.756.751.00
6, 6, 5, 6
8, 8, 5, 6
Poster
450 NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs5.756.751.00
6, 6, 3, 8
6, 8, 5, 8
Poster
451 Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation6.756.750.00
5, 8, 8, 6
5, 8, 8, 6
Poster
452 Exploring Memorization in Adversarial Training6.336.750.42
8, 8, 3
10, 8, 3, 6
Poster
453 Learning to Complete Code with Sketches6.756.750.00
8, 6, 5, 8
8, 6, 5, 8
Poster
454 miniF2F: a cross-system benchmark for formal Olympiad-level mathematics6.756.750.00
8, 5, 8, 6
8, 5, 8, 6
Poster
455 On Non-Random Missing Labels in Semi-Supervised Learning6.676.670.00
6, 6, 8
6, 6, 8
Poster
456 Invariant Causal Representation Learning for Out-of-Distribution Generalization6.336.670.33
6, 5, 8
6, 6, 8
Poster
457 Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks6.676.670.00
8, 6, 6
6, 6, 8
Poster
458 Provably Robust Adversarial Examples5.336.671.33
5, 5, 6
6, 6, 8
Poster
459 Image BERT Pre-training with Online Tokenizer6.006.670.67
5, 5, 8
6, 6, 8
Poster
460 SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations5.676.671.00
5, 6, 6
6, 8, 6
Poster
461 Solving Inverse Problems in Medical Imaging with Score-Based Generative Models5.676.671.00
5, 6, 6
8, 6, 6
Poster
462 TRAIL: Near-Optimal Imitation Learning with Suboptimal Data5.676.671.00
5, 6, 6
6, 8, 6
Poster
463 Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property6.006.670.67
6, 6, 6
6, 8, 6
Poster
464 Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space.6.006.670.67
5, 8, 5
6, 8, 6
Poster
465 The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program6.336.670.33
5, 8, 6
6, 8, 6
Poster
466 Triangle and Four Cycle Counting with Predictions in Graph Streams6.006.670.67
5, 8, 5
6, 8, 6
Poster
467 Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods4.676.672.00
3, 5, 6
6, 6, 8
Poster
468 RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning6.336.670.33
6, 8, 5
6, 8, 6
Poster
469 Neural Variational Dropout Processes6.676.670.00
6, 8, 6
6, 8, 6
Poster
470 Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators5.676.671.00
6, 5, 6
6, 8, 6
Poster
471 Properties from mechanisms: an equivariance perspective on identifiable representation learning6.676.670.00
6, 8, 6
6, 8, 6
Spotlight
472 Safe Neurosymbolic Learning with Differentiable Symbolic Execution5.336.671.33
6, 5, 5
6, 8, 6
Poster
473 Reverse Engineering of Imperceptible Adversarial Image Perturbations5.336.671.33
3, 8, 5
6, 8, 6
Poster
474 VC dimension of partially quantized neural networks in the overparametrized regime5.676.671.00
6, 5, 6
6, 6, 8
Poster
475 Multimeasurement Generative Models6.676.670.00
8, 6, 6
8, 6, 6
Poster
476 Towards Understanding the Robustness Against Evasion Attack on Categorical Data5.006.671.67
6, 3, 6
6, 8, 6
Poster
477 Zero Pixel Directional Boundary by Vector Transform6.676.670.00
6, 6, 8
6, 6, 8
Poster
478 Label Leakage and Protection in Two-party Split Learning6.006.670.67
6, 6, 6
6, 6, 8
Poster
479 BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis5.676.671.00
6, 5, 6
8, 6, 6
Poster
480 Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework6.336.670.33
8, 5, 6
8, 6, 6
Poster
481 Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery6.006.670.67
5, 5, 8
6, 6, 8
Poster
482 High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize6.506.670.17
8, 5
8, 6, 6
Poster
483 Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction5.676.671.00
6, 6, 5
8, 6, 6
Poster
484 Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification5.676.671.00
6, 5, 6
6, 6, 8
Poster
485 Practical Conditional Neural Process Via Tractable Dependent Predictions6.006.670.67
5, 5, 8
6, 6, 8
Poster
486 Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface6.336.670.33
6, 8, 5
6, 8, 6
Poster
487 Optimal Transport for Causal Discovery6.336.670.33
5, 8, 6
6, 8, 6
Spotlight
488 Dive Deeper Into Integral Pose Regression5.676.671.00
3, 6, 8
6, 6, 8
Poster
489 Information Bottleneck: Exact Analysis of (Quantized) Neural Networks6.336.670.33
6, 8, 5
6, 8, 6
Poster
490 A Class of Short-term Recurrence Anderson Mixing Methods and Their Applications6.006.670.67
6, 6, 6
8, 6, 6
Poster
491 SimVLM: Simple Visual Language Model Pretraining with Weak Supervision6.336.670.33
5, 8, 6
6, 8, 6
Poster
492 Privacy Implications of Shuffling6.676.670.00
8, 6, 6
8, 6, 6
Poster
493 End-to-End Learning of Probabilistic Hierarchies on Graphs7.006.67-0.33
6, 8
6, 8, 6
Poster
494 GradSign: Model Performance Inference with Theoretical Insights6.006.670.67
6, 6, 6
6, 8, 6
Poster
495 X-model: Improving Data Efficiency in Deep Learning with A Minimax Model6.336.670.33
8, 5, 6
8, 6, 6
Poster
496 Learning Versatile Neural Architectures by Propagating Network Codes6.676.670.00
6, 6, 8
6, 6, 8
Poster
497 Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph6.676.670.00
6, 6, 8
6, 6, 8
Poster
498 Half-Inverse Gradients for Physical Deep Learning6.336.670.33
6, 8, 5
6, 8, 6
Spotlight
499 Entroformer: A Transformer-based Entropy Model for Learned Image Compression6.676.670.00
8, 6, 6
8, 6, 6
Poster
500 Uncertainty Modeling for Out-of-Distribution Generalization6.676.670.00
6, 8, 6
6, 8, 6
Poster
501 Online Facility Location with Predictions6.176.670.50
6, 6, 6, 8, 5, 6
6, 6, 6, 8, 6, 8
Poster
502 PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning6.336.670.33
5, 6, 8
6, 6, 8
Poster
503 Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs5.676.671.00
6, 5, 6
8, 6, 6
Poster
504 When, Why, and Which Pretrained GANs Are Useful?6.676.670.00
8, 6, 6
8, 6, 6
Poster
505 Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains5.676.671.00
6, 5, 6
6, 6, 8
Poster
506 Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies5.676.671.00
6, 8, 3
6, 8, 6
Poster
507 Looking Back on Learned Experiences For Class/task Incremental Learning5.676.671.00
5, 6, 6
6, 8, 6
Spotlight
508 Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification5.336.671.33
6, 5, 5
6, 8, 6
Poster
509 Steerable Partial Differential Operators for Equivariant Neural Networks6.336.670.33
6, 8, 5
6, 8, 6
Poster
510 NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING6.336.670.33
6, 8, 5
6, 8, 6
Poster
511 P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts6.006.600.60
5, 8, 3, 6, 8
6, 8, 5, 6, 8
Poster
512 Learning meta-features for AutoML5.006.601.60
3, 3, 8, 6, 5
8, 6, 8, 6, 5
Spotlight
513 A Unified Wasserstein Distributional Robustness Framework for Adversarial Training6.606.600.00
6, 6, 8, 5, 8
6, 6, 8, 5, 8
Poster
514 Sample Selection with Uncertainty of Losses for Learning with Noisy Labels6.606.600.00
6, 8, 6, 8, 5
6, 8, 6, 8, 5
Poster
515 Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning6.406.600.20
5, 8, 8, 5, 6
6, 8, 8, 5, 6
Poster
516 Trigger Hunting with a Topological Prior for Trojan Detection6.006.500.50
5, 6, 5, 8
5, 8, 5, 8
Poster
517 Optimizing Few-Step Diffusion Samplers by Gradient Descent5.506.501.00
6, 5, 8, 3
6, 6, 8, 6
Poster
518 Fast AdvProp6.506.500.00
5, 5, 8, 8
5, 5, 8, 8
Poster
519 Learning Temporally Latent Causal Processes from General Temporal Data5.336.501.17
5, 6, 5
8, 6, 6, 6
Poster
520 Skill-based Meta-Reinforcement Learning5.506.501.00
5, 6, 5, 6
6, 8, 6, 6
Poster
521 Understanding Intrinsic Robustness Using Label Uncertainty6.256.500.25
6, 5, 8, 6
6, 6, 8, 6
Poster
522 From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness5.506.501.00
5, 6, 6, 5
6, 6, 8, 6
Poster
523 Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization6.256.500.25
8, 6, 5, 6
8, 6, 6, 6
Poster
524 Cross-Domain Imitation Learning via Optimal Transport6.256.500.25
8, 6, 6, 5
8, 6, 6, 6
Poster
525 Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization6.006.500.50
6, 6, 6, 6
8, 6, 6, 6
Poster
526 Bi-linear Value Networks for Multi-goal Reinforcement Learning5.506.501.00
5, 6, 5, 6
8, 6, 6, 6
Poster
527 Explaining Point Processes by Learning Interpretable Temporal Logic Rules5.756.500.75
5, 6, 6, 6
6, 6, 8, 6
Poster
528 ฮฒ-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap6.256.500.25
6, 6, 5, 8
6, 6, 6, 8
Poster
529 Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions6.256.500.25
6, 5, 8, 6
6, 6, 8, 6
Poster
530 On Evaluation Metrics for Graph Generative Models4.756.501.75
5, 3, 5, 6
6, 6, 6, 8
Poster
531 How Did the Model Change? Efficiently Assessing Machine Learning API Shifts6.506.500.00
6, 8, 6, 6
6, 8, 6, 6
Poster
532 Learning Prototype-oriented Set Representations for Meta-Learning6.256.500.25
6, 5, 8, 6
6, 6, 8, 6
Poster
533 Feature Kernel Distillation5.756.500.75
3, 8, 6, 6
6, 8, 6, 6
Poster
534 The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models5.756.500.75
8, 3, 6, 6
8, 6, 6, 6
Poster
535 What Do We Mean by Generalization in Federated Learning?5.006.501.50
3, 8, 3, 6
6, 8, 6, 6
Poster
536 Learning Curves for Gaussian Process Regression with Power-Law Priors and Targets4.756.501.75
5, 5, 6, 3
6, 6, 8, 6
Poster
537 Few-shot Learning via Dirichlet Tessellation Ensemble6.256.500.25
5, 6, 8, 6
6, 6, 8, 6
Poster
538 Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning6.006.500.50
5, 8, 5, 6
6, 8, 6, 6
Poster
539 On the relation between statistical learning and perceptual distances5.506.501.00
8, 5, 6, 3
8, 6, 6, 6
Spotlight
540 A Program to Build E(N)-Equivariant Steerable CNNs6.006.500.50
6, 6, 6, 6
6, 6, 6, 8
Poster
541 Variational Predictive Routing with Nested Subjective Timescales5.506.501.00
6, 5, 6, 5
8, 6, 6, 6
Poster
542 Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums4.756.501.75
6, 3, 5, 5
8, 6, 6, 6
Poster
543 PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions6.006.500.50
6, 5, 8, 5
6, 6, 8, 6
Poster
544 Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm6.006.500.50
5, 5, 8, 6
6, 6, 8, 6
Poster
545 Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations5.256.501.25
5, 5, 6, 5
6, 6, 8, 6
Poster
546 Map Induction: Compositional spatial submap learning for efficient exploration in novel environments5.256.501.25
3, 8, 5, 5
6, 8, 6, 6
Poster
547 Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?6.256.500.25
6, 6, 8, 5
6, 6, 8, 6
Poster
548 Surrogate Gap Minimization Improves Sharpness-Aware Training5.756.500.75
5, 6, 6, 6
6, 8, 6, 6
Poster
549 SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation6.676.50-0.17
6, 6, 8
6, 6, 8, 6
Poster
550 Efficient and Differentiable Conformal Prediction with General Function Classes6.256.500.25
8, 6, 5, 6
8, 6, 6, 6
Poster
551 Declarative nets that are equilibrium models6.006.500.50
6, 6, 6, 6
8, 6, 6, 6
Poster
552 Capturing Structural Locality in Non-parametric Language Models5.756.500.75
5, 8, 5, 5
6, 8, 6, 6
Poster
553 IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes6.676.50-0.17
8, 6, 6
8, 6, 6, 6
Poster
554 DEGREE: Decomposition Based Explanation for Graph Neural Networks6.006.500.50
5, 8, 6, 5
6, 8, 6, 6
Poster
555 Modular Lifelong Reinforcement Learning via Neural Composition5.256.501.25
6, 3, 6, 6
8, 6, 6, 6
Poster
556 Anisotropic Random Feature Regression in High Dimensions5.006.501.50
3, 8, 3, 6
6, 8, 6, 6
Poster
557 Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators6.176.500.33
6, 8, 6, 6, 3, 8
8, 8, 6, 6, 3, 8
Poster
558 Understanding and Improving Graph Injection Attack by Promoting Unnoticeability6.256.500.25
6, 5, 8, 6
6, 6, 8, 6
Poster
559 Huber Additive Models for Non-stationary Time Series Analysis6.006.500.50
5, 5, 6, 8
6, 6, 6, 8
Poster
560 What Makes Better Augmentation Strategies? Augment Difficult but Not too Different5.756.500.75
8, 3, 6, 6
8, 6, 6, 6
Poster
561 Lipschitz-constrained Unsupervised Skill Discovery6.256.500.25
5, 6, 8, 6
6, 6, 8, 6
Poster
562 Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting5.256.501.25
3, 5, 5, 8
8, 5, 5, 8
Poster
563 FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes5.756.500.75
5, 6, 6, 6
6, 6, 6, 8
Poster
564 Backdoor Defense via Decoupling the Training Process6.256.500.25
8, 6, 6, 5
8, 6, 6, 6
Poster
565 Bayesian Framework for Gradient Leakage5.756.500.75
6, 6, 6, 5
6, 6, 8, 6
Poster
566 On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning6.506.500.00
8, 5, 5, 8
8, 5, 5, 8
Poster
567 Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences6.256.500.25
5, 6, 6, 8
6, 6, 6, 8
Poster
568 Learning to Annotate Part Segmentation with Gradient Matching5.506.501.00
5, 6, 6, 5
6, 6, 8, 6
Poster
569 Predicting Physics in Mesh-reduced Space with Temporal Attention6.006.500.50
5, 5, 6, 8
6, 6, 6, 8
Poster
570 Online Ad Hoc Teamwork under Partial Observability6.506.500.00
8, 6, 6, 6
8, 6, 6, 6
Poster
571 On Incorporating Inductive Biases into VAEs6.256.500.25
6, 5, 6, 8
6, 6, 6, 8
Poster
572 Understanding the Variance Collapse of SVGD in High Dimensions6.506.500.00
6, 6, 6, 8
6, 6, 6, 8
Poster
573 Optimizing Neural Networks with Gradient Lexicase Selection5.256.501.25
5, 3, 5, 8
6, 6, 6, 8
Poster
574 Confidence Adaptive Anytime Pixel-Level Recognition6.006.500.50
5, 5, 6, 8
6, 6, 6, 8
Poster
575 How many degrees of freedom do we need to train deep networks: a loss landscape perspective6.506.500.00
6, 6, 8, 6
6, 6, 8, 6
Poster
576 Differentially Private Fine-tuning of Language Models6.006.500.50
6, 5, 8, 5
6, 6, 8, 6
Poster
577 Proof Artifact Co-Training for Theorem Proving with Language Models6.506.500.00
5, 8, 5, 8
5, 8, 5, 8
Poster
578 Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits6.256.500.25
6, 5, 6, 8
6, 6, 6, 8
Poster
579 Preference Conditioned Neural Multi-objective Combinatorial Optimization6.506.500.00
6, 8, 6, 6
6, 8, 6, 6
Poster
580 Gradient Step Denoiser for convergent Plug-and-Play5.506.501.00
5, 6, 8, 3
6, 6, 8, 6
Poster
581 Model-Based Offline Meta-Reinforcement Learning with Regularization5.506.501.00
8, 3, 6, 5
8, 6, 6, 6
Poster
582 How to deal with missing data in supervised deep learning?6.506.500.00
8, 5, 5, 8
8, 5, 5, 8
Poster
583 Learning Features with Parameter-Free Layers6.256.500.25
6, 5, 6, 8
6, 6, 6, 8
Poster
584 FedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning6.006.500.50
6, 8, 5, 5
6, 8, 6, 6
Poster
585 Defending Against Image Corruptions Through Adversarial Augmentations5.506.501.00
5, 5, 6, 6
6, 6, 6, 8
Poster
586 Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond6.006.500.50
5, 5, 6, 8
6, 6, 6, 8
Poster
587 Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)6.006.500.50
5, 6, 8, 5
6, 6, 8, 6
Poster
588 Learning to Downsample for Segmentation of Ultra-High Resolution Images6.256.500.25
6, 6, 5, 8
6, 6, 6, 8
Poster
589 Stiffness-aware neural network for learning Hamiltonian systems5.756.500.75
5, 6, 6, 6
6, 6, 6, 8
Poster
590 F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization6.256.500.25
5, 5, 5, 10
6, 5, 5, 10
Oral
591 GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification5.506.501.00
3, 8, 6, 5
6, 8, 6, 6
Poster
592 Effective Model Sparsification by Scheduled Grow-and-Prune Methods5.506.501.00
6, 5, 5, 6
8, 6, 6, 6
Poster
593 T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis6.256.500.25
5, 6, 6, 8
6, 6, 6, 8
Poster
594 Policy Gradients Incorporating the Future6.006.500.50
5, 5, 6, 8
6, 6, 6, 8
Poster
595 Tighter Sparse Approximation Bounds for ReLU Neural Networks6.506.500.00
6, 8, 6, 6
6, 8, 6, 6
Spotlight
596 DeSKO: Stability-Assured Robust Control with a Deep Stochastic Koopman Operator6.506.500.00
6, 6, 8, 6
6, 6, 8, 6
Poster
597 Interacting Contour Stochastic Gradient Langevin Dynamics5.756.500.75
5, 6, 6, 6
6, 6, 6, 8
Poster
598 Differentiable Expectation-Maximization for Set Representation Learning6.006.500.50
6, 6, 6, 6
8, 6, 6, 6
Poster
599 Maximum n-times Coverage for Vaccine Design5.506.501.00
6, 5, 3, 8
6, 6, 6, 8
Poster
600 Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features6.006.500.50
6, 5, 8, 5
6, 6, 8, 6
Poster
601 The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training5.506.501.00
5, 8, 3, 6
6, 8, 6, 6
Poster
602 Discovering Latent Concepts Learned in BERT5.006.501.50
6, 3, 6, 5
8, 5, 8, 5
Poster
603 Self-Supervised Inference in State-Space Models6.006.500.50
5, 8, 5, 6
6, 8, 6, 6
Poster
604 Bag of Instances Aggregation Boosts Self-supervised Distillation5.756.500.75
5, 5, 5, 8
6, 6, 6, 8
Poster
605 Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off5.756.500.75
6, 8, 6, 3
6, 8, 6, 6
Poster
606 HTLM: Hyper-Text Pre-Training and Prompting of Language Models6.256.500.25
6, 5, 8, 6
6, 6, 8, 6
Poster
607 Evaluating Model-Based Planning and Planner Amortization for Continuous Control6.256.500.25
6, 8, 6, 5
6, 8, 6, 6
Poster
608 On the Existence of Universal Lottery Tickets5.256.501.25
5, 5, 8, 3
6, 6, 8, 6
Poster
609 Reliable Adversarial Distillation with Unreliable Teachers6.256.500.25
6, 8, 6, 5
6, 8, 6, 6
Poster
610 Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation6.006.500.50
6, 6, 6, 6
6, 6, 8, 6
Poster
611 Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks5.506.501.00
8, 6, 5, 3
8, 6, 6, 6
Poster
612 Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps5.506.501.00
6, 5, 8, 3
6, 6, 8, 6
Poster
613 No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models6.506.500.00
6, 8, 6, 6
6, 8, 6, 6
Poster
614 Prototypical Contrastive Predictive Coding6.256.500.25
6, 6, 8, 5
6, 6, 8, 6
Poster
615 How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis5.006.501.50
8, 3, 6, 3
8, 6, 6, 6
Poster
616 Effect of scale on catastrophic forgetting in neural networks5.006.501.50
5, 5, 5, 5
8, 8, 5, 5
Poster
617 Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach6.506.500.00
6, 6, 8, 6
6, 6, 8, 6
Poster
618 Improving the Accuracy of Learning Example Weights for Imbalance Classification6.256.500.25
6, 8, 5, 6
6, 8, 6, 6
Poster
619 Fast Generic Interaction Detection for Model Interpretability and Compression5.756.500.75
6, 3, 8, 6
6, 6, 8, 6
Poster
620 AlphaZero-based Proof Cost Network to Aid Game Solving5.506.501.00
5, 6, 6, 5
5, 8, 8, 5
Poster
621 Implicit Bias of Adversarial Training for Deep Neural Networks6.506.500.00
8, 5, 8, 5
8, 5, 8, 5
Poster
622 Boosted Curriculum Reinforcement Learning6.676.50-0.17
6, 6, 8
6, 6, 8, 6
Poster
623 NASI: Label- and Data-agnostic Neural Architecture Search at Initialization5.756.500.75
8, 5, 5, 5
8, 6, 6, 6
Poster
624 Gradient Importance Learning for Incomplete Observations5.506.501.00
3, 6, 5, 8
6, 6, 6, 8
Poster
625 PAC Prediction Sets Under Covariate Shift6.506.500.00
6, 6, 6, 8
6, 6, 6, 8
Poster
626 Hierarchical Few-Shot Imitation with Skill Transition Models6.256.500.25
6, 6, 8, 5
6, 6, 8, 6
Poster
627 The Uncanny Similarity of Recurrence and Depth5.756.500.75
8, 5, 5, 5
8, 6, 6, 6
Poster
628 Objects in Semantic Topology5.756.500.75
8, 5, 5, 5
8, 5, 5, 8
Poster
629 EigenGame Unloaded: When playing games is better than optimizing6.506.500.00
8, 5, 8, 5
8, 5, 8, 5
Poster
630 Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning6.506.500.00
6, 6, 8, 6
6, 6, 8, 6
Poster
631 AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies5.506.501.00
5, 6
6, 8, 6, 6
Poster
632 Dealing with Non-Stationarity in MARL via Trust-Region Decomposition5.506.501.00
5, 6, 5, 6
6, 6, 6, 8
Poster
633 ViTGAN: Training GANs with Vision Transformers5.406.401.00
5, 5, 5, 6, 6
6, 6, 6, 8, 6
Spotlight
634 Predictive Modeling in the Presence of Nuisance-Induced Spurious Correlations5.506.400.90
6, 6, 5, 5
6, 8, 5, 8, 5
Poster
635 GRAND++: Graph Neural Diffusion with A Source Term5.406.401.00
8, 6, 5, 5, 3
8, 6, 6, 6, 6
Poster
636 On the Role of Neural Collapse in Transfer Learning5.806.400.60
6, 6, 6, 5, 6
6, 6, 8, 6, 6
Poster
637 Learning to Schedule Learning rate with Graph Neural Networks5.606.400.80
6, 8, 6, 5, 3
6, 8, 6, 6, 6
Poster
638 It Takes Two to Tango: Mixup for Deep Metric Learning6.206.400.20
6, 5, 6, 6, 8
6, 6, 6, 6, 8
Poster
639 WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection5.206.401.20
3, 6, 6, 6, 5
6, 6, 6, 8, 6
Poster
640 Gradient Matching for Domain Generalization5.806.400.60
6, 6, 5, 6, 6
6, 6, 6, 8, 6
Poster
641 Graph Neural Networks with Learnable Structural and Positional Representations5.606.400.80
5, 8, 5, 5, 5
6, 8, 8, 5, 5
Poster
642 On the Convergence of Certified Robust Training with Interval Bound Propagation5.676.330.67
6, 8, 3
6, 8, 5
Poster
643 Learning Distributionally Robust Models at Scale via Composite Optimization5.676.330.67
6, 5, 6
8, 5, 6
Poster
644 MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining5.336.331.00
3, 5, 8
6, 5, 8
Poster
645 Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring5.676.330.67
6, 8, 3
6, 8, 5
Poster
646 Non-Autoregressive Models are Better Multilingual Translators6.336.330.00
8, 5, 6
8, 5, 6
Poster
647 Unified Visual Transformer Compression5.336.331.00
5, 6, 5
6, 8, 5
Poster
648 Bridging Recommendation and Marketing via Recurrent Intensity Modeling5.676.330.67
6, 8, 3
6, 8, 5
Poster
649 Language-driven Semantic Segmentation5.676.330.67
5, 6, 6
5, 8, 6
Poster
650 Optimal Representations for Covariate Shift6.336.330.00
8, 5, 6
8, 5, 6
Poster
651 Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise5.336.331.00
3, 8, 5
5, 8, 6
Poster
652 CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games6.336.330.00
6, 3, 10
6, 5, 8
Poster
653 Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective6.006.330.33
5, 8, 5
5, 8, 6
Poster
654 Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization6.336.330.00
5, 8, 6
5, 8, 6
Poster
655 Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift5.336.331.00
5, 5, 6
5, 8, 6
Poster
656 Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data5.676.330.67
5, 6, 6
5, 6, 8
Poster
657 Neural Networks as Kernel Learners: The Silent Alignment Effect6.006.330.33
5, 5, 8
5, 6, 8
Poster
658 Hierarchical Variational Memory for Few-shot Learning Across Domains5.676.330.67
6, 5, 6
8, 5, 6
Poster
659 Learning to Map for Active Semantic Goal Navigation6.006.330.33
5, 8, 5
6, 8, 5
Poster
660 Sparse Attention with Learning to Hash5.336.331.00
5, 5, 6
5, 6, 8
Poster
661 Auto-scaling Vision Transformers without Training6.006.330.33
8, 5, 5
8, 6, 5
Poster
662 Autonomous Learning of Object-Centric Abstractions for High-Level Planning6.336.330.00
8, 6, 5
8, 6, 5
Poster
663 Concurrent Adversarial Learning for Large-Batch Training6.336.330.00
6, 5, 8
6, 5, 8
Poster
664 Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics5.836.330.50
6, 6, 6, 6, 5, 6
6, 6, 6, 6, 8, 6
Poster
665 Counterfactual Plans under Distributional Ambiguity6.006.330.33
8, 5, 5
8, 6, 5
Poster
666 Pareto Policy Adaptation5.336.331.00
3, 8, 5
5, 8, 6
Poster
667 Mapping conditional distributions for domain adaptation under generalized target shift6.336.330.00
5, 6, 8
5, 6, 8
Poster
668 Anti-Concentrated Confidence Bonuses For Scalable Exploration6.336.330.00
5, 6, 8
5, 6, 8
Poster
669 ViDT: An Efficient and Effective Fully Transformer-based Object Detector6.006.330.33
8, 5, 5
8, 6, 5
Poster
670 Information-theoretic Online Memory Selection for Continual Learning5.676.330.67
6, 5, 6
6, 5, 8
Poster
671 Transformers Can Do Bayesian Inference6.336.330.00
6, 5, 8
6, 5, 8
Poster
672 Neural Models for Output-Space Invariance in Combinatorial Problems6.336.330.00
8, 6, 5
8, 6, 5
Poster
673 Neural Solvers for Fast and Accurate Numerical Optimal Control5.336.331.00
5, 6, 5
5, 8, 6
Poster
674 Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information5.336.331.00
5, 5, 6
5, 6, 8
Poster
675 Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive Symptoms5.336.331.00
3, 5, 8
5, 6, 8
Poster
676 Generative Principal Component Analysis5.336.331.00
3, 8, 5
6, 8, 5
Poster
677 Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL6.006.330.33
5, 8, 5
6, 8, 5
Poster
678 DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR5.336.331.00
3, 8, 5
5, 8, 6
Poster
679 MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer6.336.330.00
5, 6, 8
5, 6, 8
Poster
680 Incremental False Negative Detection for Contrastive Learning5.006.331.33
5, 5
6, 5, 8
Poster
681 A Neural Tangent Kernel Perspective of Infinite Tree Ensembles6.336.330.00
8, 8, 3
8, 8, 3
Poster
682 Fairness Guarantees under Demographic Shift5.756.250.50
6, 5, 6, 6
6, 5, 6, 8
Poster
683 Connectome-constrained Latent Variable Model of Whole-Brain Neural Activity5.006.251.25
3, 6, 5, 6
3, 8, 8, 6
Poster
684 Automated Self-Supervised Learning for Graphs6.006.250.25
6, 5, 8, 5
6, 5, 8, 6
Poster
685 Knowledge Infused Decoding6.006.250.25
5, 5, 8, 6
6, 5, 8, 6
Poster
686 Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining6.006.250.25
5, 6, 8, 5
6, 6, 8, 5
Spotlight
687 Distributional Reinforcement Learning with Monotonic Splines6.006.250.25
5, 6, 8, 5
6, 6, 8, 5
Poster
688 AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation6.256.250.00
5, 6, 6, 8
5, 6, 6, 8
Poster
689 Multitask Prompted Training Enables Zero-Shot Task Generalization6.256.250.00
8, 3, 6, 8
8, 3, 6, 8
Spotlight
690 Learning Value Functions from Undirected State-only Experience6.006.250.25
5, 8, 6, 5
5, 8, 6, 6
Poster
691 Finding an Unsupervised Image Segmenter in each of your Deep Generative Models6.256.250.00
6, 5, 6, 8
6, 5, 6, 8
Poster
692 Neural Processes with Stochastic Attention: Paying more attention to the context dataset5.506.250.75
5, 5, 6, 6
8, 5, 6, 6
Poster
693 SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search5.756.250.50
8, 3, 6, 6
8, 5, 6, 6
Poster
694 Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion6.256.250.00
6, 6, 8, 5
6, 6, 8, 5
Oral
695 Semi-relaxed Gromov-Wasserstein divergence and applications on graphs6.256.250.00
8, 5, 6, 6
8, 5, 6, 6
Poster
696 Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks5.506.250.75
6, 5, 6, 5
6, 5, 8, 6
Poster
697 Neural Link Prediction with Walk Pooling5.756.250.50
8, 6, 6, 3
8, 6, 6, 5
Poster
698 Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference5.006.251.25
6, 5, 3, 6
6, 8, 3, 8
Poster
699 Adversarial Retriever-Ranker for Dense Text Retrieval6.006.250.25
6, 5, 8, 5
6, 6, 8, 5
Poster
700 Provable Learning-based Algorithm For Sparse Recovery5.006.251.25
3, 6, 5, 6
5, 6, 6, 8
Poster
701 Goal-Directed Planning via Hindsight Experience Replay5.506.250.75
5, 8, 3, 6
6, 8, 3, 8
Poster
702 GDA-AM: ON THE EFFECTIVENESS OF SOLVING MIN-IMAX OPTIMIZATION VIA ANDERSON MIXING4.756.251.50
3, 6, 5, 5
6, 6, 8, 5
Poster
703 Increasing the Cost of Model Extraction with Calibrated Proof of Work5.756.250.50
6, 3, 6, 8
6, 3, 8, 8
Spotlight
704 The Essential Elements of Offline RL via Supervised Learning4.756.251.50
5, 6, 3, 5
8, 6, 5, 6
Poster
705 Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism6.256.250.00
8, 6, 6, 5
8, 6, 6, 5
Poster
706 Conditional Contrastive Learning with Kernel5.506.250.75
5, 5, 6, 6
5, 6, 6, 8
Poster
707 Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image5.756.250.50
6, 6, 8, 3
6, 6, 8, 5
Poster
708 The Three Stages of Learning Dynamics in High-dimensional Kernel Methods6.256.250.00
8, 6, 5, 6
8, 6, 5, 6
Poster
709 FedBABU: Toward Enhanced Representation for Federated Image Classification6.006.250.25
5, 5, 6, 8
5, 6, 6, 8
Poster
710 Curriculum learning as a tool to uncover learning principles in the brain5.006.251.25
5, 6, 6, 3
6, 6, 8, 5
Poster
711 Model Zoo: A Growing Brain That Learns Continually6.256.250.00
6, 6, 8, 5
6, 6, 8, 5
Poster
712 Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series5.506.250.75
5, 6, 5, 6
5, 8, 6, 6
Poster
713 Fast Model Editing at Scale6.336.25-0.08
8, 8, 3
8, 8, 3, 6
Poster
714 Memorizing Transformers5.756.250.50
8, 6, 3, 6
8, 6, 5, 6
Spotlight
715 TAda! Temporally-Adaptive Convolutions for Video Understanding5.506.250.75
5, 5, 6, 6
5, 6, 8, 6
Poster
716 Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions5.006.251.25
5, 6, 3, 6
6, 8, 5, 6
Poster
717 Step-unrolled Denoising Autoencoders for Text Generation5.506.250.75
6, 5, 5, 6
6, 5, 6, 8
Poster
718 Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL6.256.250.00
8, 3, 8, 6
8, 3, 8, 6
Poster
719 Lossless Compression with Probabilistic Circuits5.506.250.75
6, 8, 5, 3
6, 8, 5, 6
Spotlight
720 Neural Parameter Allocation Search5.006.251.25
3, 6, 6, 5
6, 8, 6, 5
Poster
721 Generalized Kernel Thinning6.256.250.00
6, 8, 5, 6
6, 8, 5, 6
Poster
722 Linking Emergent and Natural Languages via Corpus Transfer6.256.250.00
8, 6, 8, 3
8, 6, 8, 3
Spotlight
723 Do deep networks transfer invariances across classes?5.256.251.00
3, 5, 5, 8
6, 5, 6, 8
Poster
724 Transferable Visual Control Policies Through Robot-Awareness5.506.250.75
8, 3, 6, 5
8, 6, 6, 5
Poster
725 Deep Point Cloud Reconstruction6.256.250.00
5, 8, 6, 6
5, 8, 6, 6
Poster
726 Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting6.256.250.00
8, 6, 6, 5
8, 6, 6, 5
Poster
727 Collapse by Conditioning: Training Class-conditional GANs with Limited Data6.006.250.25
5, 6, 8, 5
6, 6, 8, 5
Poster
728 Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients6.006.250.25
6, 5, 5, 8
6, 6, 5, 8
Poster
729 Is Importance Weighting Incompatible with Interpolating Classifiers?5.676.250.58
8, 6, 3
8, 6, 5, 6
Poster
730 Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings6.256.250.00
3, 6, 8, 8
3, 6, 8, 8
Poster
731 How Much Can CLIP Benefit Vision-and-Language Tasks?5.756.250.50
8, 6, 3, 6
8, 6, 5, 6
Poster
732 It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation5.006.251.25
5, 6, 3, 6
8, 6, 5, 6
Poster
733 Large-Scale Representation Learning on Graphs via Bootstrapping6.006.250.25
5, 6, 8, 5
5, 6, 8, 6
Poster
734 TRGP: Trust Region Gradient Projection for Continual Learning6.006.250.25
3, 5, 8, 8
3, 6, 8, 8
Spotlight
735 Neural Contextual Bandits with Deep Representation and Shallow Exploration6.756.25-0.50
8, 5, 8, 6
8, 3, 8, 6
Poster
736 Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models6.256.250.00
6, 8, 6, 5
6, 8, 6, 5
Poster
737 Discriminative Similarity for Data Clustering6.256.250.00
6, 6, 8, 5
6, 6, 8, 5
Poster
738 CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting6.006.250.25
5, 5, 6, 8
5, 6, 6, 8
Poster
739 The Evolution of Uncertainty of Learning in Games5.756.250.50
6, 6, 6, 5
6, 6, 8, 5
Poster
740 Enabling Arbitrary Translation Objectives with Adaptive Tree Search6.006.250.25
5, 6, 5, 8
6, 6, 5, 8
Poster
741 CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention5.756.250.50
6, 5, 6, 6
8, 5, 6, 6
Poster
742 Subspace Regularizers for Few-Shot Class Incremental Learning5.756.250.50
5, 5, 8, 5
6, 6, 8, 5
Poster
743 Explainable GNN-Based Models over Knowledge Graphs5.256.251.00
5, 5, 5, 6
8, 5, 6, 6
Poster
744 Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning4.676.251.58
5, 3, 6
6, 5, 6, 8
Poster
745 R4D: Utilizing Reference Objects for Long-Range Distance Estimation6.256.250.00
6, 6, 8, 5
6, 6, 8, 5
Poster
746 Relational Multi-Task Learning: Modeling Relations between Data and Tasks6.256.250.00
8, 6, 6, 5
8, 6, 6, 5
Spotlight
747 A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease5.756.250.50
6, 3, 8, 6
6, 5, 8, 6
Poster
748 CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals6.006.250.25
5, 8, 5, 6
5, 8, 6, 6
Poster
749 How Low Can We Go: Trading Memory for Error in Low-Precision Training5.756.250.50
5, 6, 6, 6
5, 6, 6, 8
Poster
750 Boosting the Certified Robustness of L-infinity Distance Nets5.756.250.50
8, 5, 5, 5
8, 6, 5, 6
Poster
751 Memory Augmented Optimizers for Deep Learning6.256.250.00
8, 6, 6, 5
8, 6, 6, 5
Poster
752 Gaussian Mixture Convolution Networks6.336.25-0.08
6, 8, 5
6, 8, 6, 5
Poster
753 Evidential Turing Processes5.506.250.75
5, 5, 6, 6
8, 5, 6, 6
Poster
754 A global convergence theory for deep ReLU implicit networks via over-parameterization6.256.250.00
8, 8, 6, 3
8, 8, 6, 3
Poster
755 How Well Does Self-Supervised Pre-Training Perform with Streaming Data?6.006.250.25
6, 5, 8, 5
6, 5, 8, 6
Poster
756 Understanding and Preventing Capacity Loss in Reinforcement Learning5.506.250.75
3, 5, 6, 8
3, 6, 8, 8
Spotlight
757 Scale Efficiently: Insights from Pretraining and Finetuning Transformers6.256.250.00
6, 6, 5, 8
6, 6, 5, 8
Poster
758 Learning to Extend Molecular Scaffolds with Structural Motifs6.256.250.00
8, 8, 3, 6
8, 8, 3, 6
Poster
759 Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training6.256.250.00
8, 8, 6, 3
8, 8, 6, 3
Poster
760 Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification5.756.250.50
6, 5, 6, 6
8, 5, 6, 6
Poster
761 DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals5.006.251.25
5, 6, 3, 6
6, 8, 3, 8
Poster
762 Taming Sparsely Activated Transformer with Stochastic Experts5.756.250.50
6, 8, 3, 6
6, 8, 5, 6
Poster
763 Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation5.506.250.75
6, 5, 5, 6
6, 5, 6, 8
Poster
764 Unsupervised Disentanglement with Tensor Product Representations on the Torus6.256.250.00
3, 8, 6, 8
3, 8, 6, 8
Poster
765 Multi-Agent MDP Homomorphic Networks6.006.250.25
5, 8, 5, 6
5, 8, 6, 6
Poster
766 DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning6.006.250.25
5, 6, 8, 5
6, 6, 8, 5
Poster
767 Online Coreset Selection for Rehearsal-based Continual Learning5.756.250.50
5, 6, 6, 6
5, 8, 6, 6
Poster
768 Mirror Descent Policy Optimization5.756.250.50
3, 6, 8, 6
5, 6, 8, 6
Poster
769 On-Policy Model Errors in Reinforcement Learning6.006.250.25
5, 5, 6, 8
6, 5, 6, 8
Poster
770 Learning Multimodal VAEs through Mutual Supervision6.006.250.25
6, 8, 5, 5
6, 8, 5, 6
Spotlight
771 In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications4.756.251.50
3, 3, 8, 5
6, 3, 8, 8
Poster
772 Multi-Mode Deep Matrix and Tensor Factorization6.336.25-0.08
8, 6, 5
8, 6, 5, 6
Poster
773 Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage6.256.250.00
6, 6, 8, 5
6, 6, 8, 5
Poster
774 Scale Mixtures of Neural Network Gaussian Processes6.006.250.25
5, 6, 5, 8
5, 6, 6, 8
Poster
775 Monotonic Differentiable Sorting Networks6.006.250.25
8, 6, 5, 5
8, 6, 6, 5
Poster
776 Target-Side Data Augmentation for Sequence Generation4.756.251.50
3, 5, 5, 6
5, 6, 6, 8
Poster
777 Quadtree Attention for Vision Transformers6.256.250.00
6, 8, 5, 6
6, 8, 5, 6
Poster
778 Igeood: An Information Geometry Approach to Out-of-Distribution Detection5.006.251.25
3, 6, 5, 6
5, 8, 6, 6
Poster
779 Continual Normalization: Rethinking Batch Normalization for Online Continual Learning5.506.250.75
6, 5, 6, 5
6, 5, 8, 6
Poster
780 On feature learning in shallow and multi-layer neural networks with global convergence guarantees5.506.250.75
3, 8, 6, 5
3, 8, 8, 6
Poster
781 Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum6.256.250.00
8, 6, 8, 3
8, 6, 8, 3
Poster
782 Generative Modeling with Optimal Transport Maps6.006.250.25
6, 8, 5, 5
6, 8, 6, 5
Poster
783 Multi-Task Processes6.006.250.25
6, 5, 8, 5
6, 5, 8, 6
Poster
784 Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability5.506.250.75
6, 3, 8, 5
8, 3, 8, 6
Poster
785 Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning6.256.250.00
5, 6, 6, 8
5, 6, 6, 8
Poster
786 GATSBI: Generative Adversarial Training for Simulation-Based Inference6.006.250.25
8, 5, 5, 6
8, 6, 5, 6
Poster
787 Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression6.006.250.25
5, 6, 5, 8
6, 6, 5, 8
Poster
788 Rethinking Class-Prior Estimation for Positive-Unlabeled Learning6.006.250.25
6, 5, 8, 5
6, 6, 8, 5
Poster
789 Top-N: Equivariant Set and Graph Generation without Exchangeability5.006.251.25
3, 6, 6, 5
5, 8, 6, 6
Poster
790 FastSHAP: Real-Time Shapley Value Estimation5.006.251.25
3, 6, 5, 6
5, 6, 8, 6
Poster
791 Autoregressive Diffusion Models6.256.250.00
6, 5, 8, 6
6, 5, 8, 6
Poster
792 Maximum Entropy RL (Provably) Solves Some Robust RL Problems5.756.250.50
6, 6, 6, 5
6, 8, 6, 5
Poster
793 Constraining Linear-chain CRFs to Regular Languages5.756.250.50
3, 8, 6, 6
5, 8, 6, 6
Poster
794 Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data6.256.250.00
8, 6, 3, 8
8, 6, 3, 8
Poster
795 Disentanglement Analysis with Partial Information Decomposition5.506.250.75
3, 5, 6, 8
6, 5, 6, 8
Poster
796 Hindsight Foresight Relabeling for Meta-Reinforcement Learning5.006.251.25
3, 6, 5, 6
5, 8, 6, 6
Poster
797 Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction6.256.250.00
5, 6, 6, 8
5, 6, 6, 8
Poster
798 Self-ensemble Adversarial Training for Improved Robustness5.006.251.25
5, 6, 3, 6
6, 6, 5, 8
Poster
799 An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch6.256.250.00
5, 6, 8, 6
5, 6, 8, 6
Poster
800 Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System6.256.250.00
6, 5, 8, 6
6, 5, 8, 6
Poster
801 Non-Parallel Text Style Transfer with Self-Parallel Supervision5.006.201.20
6, 6, 5, 3, 5
8, 6, 8, 3, 6
Poster
802 Cross-Domain Lossy Compression as Optimal Transport with an Entropy Bottleneck6.206.200.00
3, 8, 6, 6, 8
3, 8, 6, 6, 8
Poster
803 NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training6.206.200.00
6, 5, 6, 8, 6
6, 5, 6, 8, 6
Poster
804 Policy Smoothing for Provably Robust Reinforcement Learning5.406.200.80
6, 6, 6, 6, 3
6, 8, 6, 6, 5
Poster
805 The Spectral Bias of Polynomial Neural Networks5.406.200.80
3, 6, 6, 6, 6
5, 6, 6, 8, 6
Poster
806 Fair Normalizing Flows5.006.201.20
6, 3, 5, 5, 6
6, 5, 8, 6, 6
Poster
807 Understanding Dimensional Collapse in Contrastive Self-supervised Learning5.606.200.60
6, 3, 8, 6, 5
6, 6, 8, 6, 5
Poster
808 A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features6.006.200.20
5, 8, 6, 6, 5
5, 8, 6, 6, 6
Poster
809 BiBERT: Accurate Fully Binarized BERT6.006.200.20
5, 6, 5, 6, 8
6, 6, 5, 6, 8
Poster
810 Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective5.806.200.40
5, 5, 6, 5, 8
6, 5, 6, 6, 8
Poster
811 OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION6.006.200.20
5, 5, 8, 6, 6
6, 5, 8, 6, 6
Poster
812 On Redundancy and Diversity in Cell-based Neural Architecture Search6.006.200.20
5, 5, 8, 6, 6
5, 6, 8, 6, 6
Poster
813 Efficient Neural Causal Discovery without Acyclicity Constraints6.006.200.20
6, 6, 5, 8, 5
6, 6, 5, 8, 6
Poster
814 Top-label calibration and multiclass-to-binary reductions5.506.000.50
6, 3, 8, 5
6, 5, 8, 5
Poster
815 PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication5.756.000.25
6, 5, 6, 6
6, 6, 6, 6
Poster
816 Auto-Transfer: Learning to Route Transferable Representations5.006.001.00
5, 5, 5, 5
6, 6, 6, 6
Poster
817 FILM: Following Instructions in Language with Modular Methods6.256.00-0.25
5, 6, 8, 6
6, 6, 6, 6
Poster
818 Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers6.006.000.00
6, 6, 6
6, 6, 6, 6
Poster
819 Language model compression with weighted low-rank factorization5.336.000.67
6, 5, 5
6, 6, 6
Poster
820 The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders4.676.001.33
3, 5, 6
6, 6, 6
Poster
821 Prototype memory and attention mechanisms for few shot image generation6.006.000.00
8, 5, 5
8, 5, 5
Poster
822 LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL5.506.000.50
6, 5, 8, 3
6, 5, 8, 5
Poster
823 CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization5.506.000.50
5, 5, 6, 6
5, 5, 8, 6
Poster
824 LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning5.256.000.75
5, 8, 3, 5
5, 8, 6, 5
Poster
825 Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods5.256.000.75
5, 6, 5, 5
6, 6, 6, 6
Poster
826 Learning Representation from Neural Fisher Kernel with Low-rank Approximation6.006.000.00
6, 6, 6
6, 6, 6
Poster
827 Discrete Representations Strengthen Vision Transformer Robustness5.336.000.67
5, 8, 3
5, 8, 3, 8
Poster
828 Modeling Label Space Interactions in Multi-label Classification using Box Embeddings6.006.000.00
6, 5, 8, 5
6, 5, 8, 5
Poster
829 Graph-Guided Network for Irregularly Sampled Multivariate Time Series5.336.000.67
5, 3, 8
5, 5, 8
Poster
830 Learning to Dequantise with Truncated Flows5.336.000.67
5, 5, 6
6, 6, 6
Poster
831 Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning5.006.001.00
6, 3, 6
6, 6, 6
Poster
832 Autonomous Reinforcement Learning: Formalism and Benchmarking6.006.000.00
3, 8, 5, 8
3, 8, 5, 8
Poster
833 VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects5.006.001.00
6, 6, 3
6, 6, 6
Poster
834 An Agnostic Approach to Federated Learning with Class Imbalance5.506.000.50
6, 6, 5, 5
6, 6, 6, 6
Poster
835 Generalization Through the Lens of Leave-One-Out Error4.676.001.33
3, 5, 6
6, 6, 6
Poster
836 Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound4.806.001.20
5, 5, 5, 6, 3
6, 6, 6, 6, 6
Poster
837 Augmented Sliced Wasserstein Distances6.006.000.00
6, 6, 6
6, 6, 6, 6
Poster
838 W-CTC: a Connectionist Temporal Classification Loss with Wild Cards5.756.000.25
6, 6, 5, 6
6, 6, 6, 6
Poster
839 DictFormer: Tiny Transformer with Shared Dictionary5.256.000.75
6, 5, 5, 5
6, 6, 6, 6
Poster
840 Nonlinear ICA Using Volume-Preserving Transformations5.806.000.20
6, 6, 6, 6, 5
6, 6, 6, 6, 6
Poster
841 Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation4.676.001.33
5, 3, 6
6, 6, 6
Poster
842 PoNet: Pooling Network for Efficient Token Mixing in Long Sequences5.756.000.25
5, 5, 5, 8
5, 6, 5, 8
Poster
843 DISSECT: Disentangled Simultaneous Explanations via Concept Traversals5.756.000.25
6, 6, 5, 6
6, 6, 6, 6
Poster
844 Is Homophily a Necessity for Graph Neural Networks?5.256.000.75
6, 5, 5, 5
6, 6, 6, 6
Poster
845 Query Embedding on Hyper-Relational Knowledge Graphs6.006.000.00
8, 5, 5, 6, 6
8, 5, 5, 6, 6
Poster
846 Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation5.006.001.00
6, 3, 5, 6
6, 6, 6, 6
Poster
847 Selective Ensembles for Consistent Predictions5.506.000.50
6, 5, 5, 6
8, 5, 5, 6
Poster
848 Open-World Semi-Supervised Learning5.806.000.20
6, 6, 6, 6, 5
6, 6, 6, 6, 6
Poster
849 On the benefits of maximum likelihood estimation for Regression and Forecasting5.336.000.67
5, 3, 8
5, 5, 8
Poster
850 An Explanation of In-context Learning as Implicit Bayesian Inference5.506.000.50
5, 6, 6, 5
6, 6, 6, 6
Poster
851 Stein Latent Optimization for Generative Adversarial Networks5.506.000.50
6, 5, 6, 5
6, 6, 6, 6
Poster
852 Pseudo Numerical Methods for Diffusion Models on Manifolds6.006.000.00
5, 8, 5, 6
5, 8, 5, 6
Poster
853 Discrepancy-Based Active Learning for Domain Adaptation5.756.000.25
6, 6, 5, 6
6, 6, 6, 6
Poster
854 Adversarial Unlearning of Backdoors via Implicit Hypergradient5.256.000.75
6, 5, 5, 5
6, 6, 6, 6
Poster
855 Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks5.506.000.50
3, 6, 8, 5
3, 8, 8, 5
Poster
856 Offline Reinforcement Learning for Large Scale Language Action Spaces5.006.001.00
6, 5, 3, 6
6, 6, 6, 6
Poster
857 Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs5.256.000.75
6, 5, 5, 5
6, 6, 6, 6
Poster
858 Learning Weakly-supervised Contrastive Representations5.506.000.50
3, 5, 6, 8
5, 5, 6, 8
Poster
859 Generalizing Few-Shot NAS with Gradient Matching5.756.000.25
6, 5, 6, 6
6, 6, 6, 6
Poster
860 THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling5.006.001.00
5, 5, 5, 5
6, 6, 6, 6
Poster
861 SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning5.336.000.67
5, 6, 5
6, 6, 6
Poster
862 Scaling the Depth of Vision Transformers via the Fourier Domain Analysis5.336.000.67
5, 5, 6
6, 6, 6
Poster
863 Illiterate DALLโ‹…E Learns to Compose5.336.000.67
5, 6, 5
6, 6, 6
Poster
864 Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning4.756.001.25
5, 6, 5, 3
6, 6, 6, 6
Poster
865 Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias5.006.001.00
6, 6, 5, 3
8, 6, 5, 5
Poster
866 Online Adversarial Attacks5.256.000.75
5, 5, 5, 6
5, 5, 6, 8
Poster
867 Provably convergent quasistatic dynamics for mean-field two-player zero-sum games5.756.000.25
6, 6, 6, 5
6, 6, 6, 6
Poster
868 Space-Time Graph Neural Networks6.006.000.00
5, 5, 8
5, 5, 8
Poster
869 IGLU: Efficient GCN Training via Lazy Updates5.676.000.33
6, 5, 6
6, 6, 6
Poster
870 On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks4.336.001.67
5, 3, 5
6, 6, 6
Poster
871 RegionViT: Regional-to-Local Attention for Vision Transformers6.006.000.00
6, 6, 6, 6
6, 6, 6, 6
Poster
872 Group equivariant neural posterior estimation5.256.000.75
5, 6, 5, 5
5, 8, 5, 6
Poster
873 GeneDisco: A Benchmark for Experimental Design in Drug Discovery4.676.001.33
3, 6, 5
6, 6, 6
Poster
874 One After Another: Learning Incremental Skills for a Changing World4.756.001.25
6, 5, 3, 5
6, 6, 6, 6
Poster
875 Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios5.006.001.00
6, 5, 6, 3
6, 5, 8, 5
Poster
876 Universalizing Weak Supervision5.256.000.75
8, 3, 5, 5
8, 3, 8, 5
Poster
877 Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization4.676.001.33
5, 6, 3
5, 6, 5, 8
Poster
878 The Rich Get Richer: Disparate Impact of Semi-Supervised Learning5.506.000.50
5, 5, 6, 6
6, 6, 6, 6
Poster
879 On the role of population heterogeneity in emergent communication5.006.001.00
3, 6, 6, 5
6, 6, 6, 6
Poster
880 MoReL: Multi-omics Relational Learning6.006.000.00
8, 6, 5, 5
8, 6, 5, 5
Poster
881 Topological Graph Neural Networks5.756.000.25
6, 5, 6, 6
6, 6, 6, 6
Poster
882 Measuring CLEVRness: Black-box Testing of Visual Reasoning Models5.676.000.33
6, 6, 5
6, 6, 6
Poster
883 TPU-GAN: Learning temporal coherence from dynamic point cloud sequences5.806.000.20
6, 6, 6, 6, 5
6, 6, 6, 6, 6
Poster
884 OntoProtein: Protein Pretraining With Gene Ontology Embedding5.676.000.33
6, 5, 6
6, 6, 6
Poster
885 Orchestrated Value Mapping for Reinforcement Learning5.676.000.33
6, 6, 5
6, 6, 6
Poster
886 Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization5.506.000.50
5, 6, 6, 5
6, 6, 6, 6
Poster
887 Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset5.256.000.75
8, 5, 3, 5
8, 5, 5, 6
Poster
888 Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games5.256.000.75
5, 5, 5, 6
6, 6, 6, 6
Poster
889 Training Transition Policies via Distribution Matching for Complex Tasks6.006.000.00
6, 6, 6
6, 6, 6
Poster
890 On Robust Prefix-Tuning for Text Classification5.506.000.50
6, 5, 6, 5
6, 6, 6, 6
Poster
891 The Efficiency Misnomer4.756.001.25
3, 6, 5, 5
5, 6, 5, 8
Poster
892 Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations5.756.000.25
5, 5, 5, 8
5, 6, 5, 8
Poster
893 Neural Methods for Logical Reasoning over Knowledge Graphs5.256.000.75
8, 5, 3, 5
8, 5, 6, 5
Poster
894 Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes5.756.000.25
6, 6, 5, 6
6, 6, 6, 6
Poster
895 Charformer: Fast Character Transformers via Gradient-based Subword Tokenization6.006.000.00
6, 8, 6, 5, 5
6, 8, 6, 5, 5
Poster
896 Signing the Supermask: Keep, Hide, Invert5.006.001.00
5, 5, 5
5, 5, 8, 6
Poster
897 Attention-based Interpretability with Concept Transformers5.256.000.75
5, 3, 5, 8
5, 6, 5, 8
Poster
898 Normalization of Language Embeddings for Cross-Lingual Alignment5.606.000.40
8, 6, 5, 3, 6
8, 6, 5, 3, 8
Poster
899 Offline Reinforcement Learning with In-sample Q-Learning5.506.000.50
8, 5, 6, 3
8, 5, 6, 5
Poster
900 Differentiable DAG Sampling6.006.000.00
5, 8, 5
5, 8, 5
Poster
901 On the Convergence of mSGD and AdaGrad for Stochastic Optimization5.676.000.33
6, 5, 6
6, 6, 6
Poster
902 Neural Stochastic Dual Dynamic Programming5.756.000.25
6, 6, 6, 5
6, 6, 6, 6
Poster
903 ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind5.336.000.67
5, 5, 6
6, 6, 6
Poster
904 Learning Invariant Representations on Multilingual Language Models for Unsupervised Cross-Lingual Transfer5.506.000.50
5, 6, 6, 5
6, 6, 6, 6
Poster
905 Learning Curves for SGD on Structured Features5.756.000.25
5, 5, 5, 8
5, 5, 6, 8
Poster
906 Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs4.336.001.67
3, 5, 5
6, 6, 6
Poster
907 Recursive Disentanglement Network5.256.000.75
3, 6, 6, 6
6, 6, 6, 6
Poster
908 MAML is a Noisy Contrastive Learner5.336.000.67
6, 5, 5
8, 5, 5
Poster
909 L0-Sparse Canonical Correlation Analysis6.006.000.00
6, 6, 6, 6
6, 6, 6, 6
Poster
910 Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval5.756.000.25
6, 5, 6, 6
6, 6, 6, 6
Poster
911 A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks5.506.000.50
6, 5, 3, 8
8, 5, 3, 8
Poster
912 Transfer RL across Observation Feature Spaces via Model-Based Regularization5.256.000.75
5, 3, 8, 5
5, 5, 8, 6
Poster
913 A Theory of Tournament Representations5.256.000.75
3, 5, 5, 8
5, 5, 6, 8
Poster
914 Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning5.506.000.50
5, 5, 6, 6
6, 6, 6, 6
Poster
915 Conditioning Sequence-to-sequence Networks with Learned Activations5.676.000.33
6, 5, 6
6, 6, 6
Poster
916 PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series5.506.000.50
5, 6, 6, 5
6, 6, 6, 6
Poster
917 Controlling the Complexity and Lipschitz Constant improves Polynomial Nets6.006.000.00
5, 8, 6, 5
5, 8, 6, 5
Poster
918 Vector-quantized Image Modeling with Improved VQGAN5.506.000.50
6, 6, 5, 5
6, 6, 6, 6
Poster
919 Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov Game5.606.000.40
5, 6, 6, 6, 5
6, 6, 6, 6, 6
Poster
920 Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix5.336.000.67
5, 6, 5
6, 6, 6
Poster
921 BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models6.006.000.00
8, 3, 8, 5
8, 3, 8, 5
Poster
922 Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration5.806.000.20
6, 6, 6, 6, 5
6, 6, 6, 6, 6
Poster
923 Few-Shot Backdoor Attacks on Visual Object Tracking5.336.000.67
6, 5, 5
6, 6, 6
Poster
924 Generative Pseudo-Inverse Memory6.006.000.00
5, 8, 5
5, 8, 5
Poster
925 PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior5.006.001.00
5, 5, 5, 5
6, 6, 6, 6
Poster
926 How Attentive are Graph Attention Networks?6.006.000.00
8, 6, 5, 5
8, 6, 5, 5
Poster
927 Dropout Q-Functions for Doubly Efficient Reinforcement Learning4.676.001.33
5, 3, 6
6, 6, 6
Poster
928 Evaluating Disentanglement of Structured Latent Representations5.676.000.33
5, 6, 6
6, 6, 6
Poster
929 MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts5.676.000.33
6, 5, 6
6, 6, 6
Poster
930 iFlood: A Stable and Effective Regularizer5.256.000.75
5, 5, 6, 5
6, 6, 6, 6
Poster
931 An Operator Theoretic View On Pruning Deep Neural Networks6.256.00-0.25
5, 6, 8, 6
6, 6, 6, 6
Poster
932 Optimizer Amalgamation5.756.000.25
5, 6, 6, 6
6, 6, 6, 6
Poster
933 Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models5.336.000.67
5, 6, 5
6, 6, 6
Poster
934 Neural graphical modelling in continuous-time: consistency guarantees and algorithms6.506.00-0.50
8, 5
8, 5, 5
Poster
935 Adaptive Wavelet Transformer Network for 3D Shape Representation Learning5.756.000.25
6, 6, 5, 6
6, 6, 6, 6
Poster
936 Transferable Adversarial Attack based on Integrated Gradients5.756.000.25
5, 5, 8, 5
5, 6, 8, 5
Poster
937 Learning Graphon Mean Field Games and Approximate Nash Equilibria6.006.000.00
8, 5, 5, 6
8, 5, 6, 5
Poster
938 Benchmarking the Spectrum of Agent Capabilities5.756.000.25
5, 5, 5, 8
6, 5, 5, 8
Poster
939 Generalisation in Lifelong Reinforcement Learning through Logical Composition4.675.831.17
5, 3, 3, 6, 6, 5
5, 5, 5, 8, 6, 6
Poster
940 Graph-based Nearest Neighbor Search in Hyperbolic Spaces7.005.80-1.20
8, 6
6, 6, 6, 6, 5
Poster
941 Why Propagate Alone? Parallel Use of Labels and Features on Graphs5.405.800.40
5, 5, 3, 6, 8
5, 5, 5, 6, 8
Poster
942 Symbolic Learning to Optimize: Towards Interpretability and Scalability4.805.801.00
6, 5, 3, 5, 5
6, 6, 5, 6, 6
Poster
943 Regularized Autoencoders for Isometric Representation Learning5.805.800.00
6, 5, 5, 8, 5
6, 5, 5, 8, 5
Poster
944 Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation5.405.800.40
5, 5, 6, 5, 6
5, 6, 6, 6, 6
Poster
945 Relational Learning with Variational Bayes5.605.800.20
5, 6, 5, 6, 6
5, 6, 6, 6, 6
Poster
946 Amortized Implicit Differentiation for Stochastic Bilevel Optimization5.605.800.20
3, 6, 5, 8, 6
3, 6, 6, 8, 6
Poster
947 A Generalized Weighted Optimization Method for Computational Learning and Inversion5.255.800.55
6, 6, 3, 6
6, 6, 5, 6, 6
Poster
948 Towards Empirical Sandwich Bounds on the Rate-Distortion Function4.255.751.50
1, 5, 6, 5
3, 6, 8, 6
Poster
949 Network Augmentation for Tiny Deep Learning5.255.750.50
5, 5, 8, 3
6, 6, 8, 3
Poster
950 QUERY-EFFICIENT DECISION-BASED SPARSE ATTACKS AGAINST BLACK-BOX MACHINE LEARNING MODELS5.755.750.00
5, 6, 6, 6
5, 6, 6, 6
Poster
951 Graph Condensation for Graph Neural Networks5.255.750.50
5, 5, 6, 5
6, 5, 6, 6
Poster
952 A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model5.505.750.25
5, 8, 6, 3
6, 8, 6, 3
Poster
953 An Information Fusion Approach to Learning with Instance-Dependent Label Noise5.505.750.25
6, 5, 6, 5
8, 5, 5, 5
Poster
954 From Intervention to Domain Transportation: A Novel Perspective to Optimize Recommendation5.675.750.08
5, 6, 6
5, 6, 6, 6
Poster
955 GradMax: Growing Neural Networks using Gradient Information5.005.750.75
5, 5, 5, 5
5, 6, 6, 6
Poster
956 Provable Adaptation across Multiway Domains via Representation Learning5.255.750.50
6, 3, 6, 6
6, 3, 8, 6
Poster
957 Learning Efficient Online 3D Bin Packing on Packing Configuration Trees5.255.750.50
6, 6, 6, 3
8, 6, 6, 3
Poster
958 Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences5.005.750.75
6, 5, 6, 3
6, 5, 6, 6
Poster
959 A Comparison of Variable Selection Methods for Blockwise Diagonal Designs5.505.750.25
5, 6, 3, 8
6, 6, 3, 8
Poster
960 A Zest of LIME: Towards Architecture-Independent Model Distances5.255.750.50
6, 6, 6, 3
6, 6, 8, 3
Poster
961 Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks5.505.750.25
6, 6, 5, 5
6, 6, 6, 5
Poster
962 Task-Induced Representation Learning4.755.751.00
5, 5, 3, 6
5, 6, 6, 6
Poster
963 Constructing Orthogonal Convolutions in an Explicit Manner5.335.750.42
5, 6, 5
8, 6, 3, 6
Poster
964 Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning5.505.750.25
6, 6, 5, 5
6, 6, 6, 5
Poster
965 FP-DETR: Detection Transformer Advanced by Fully Pre-training5.505.750.25
5, 6, 6, 5
5, 6, 6, 6
Poster
966 Reward Uncertainty for Exploration in Preference-based Reinforcement Learning4.005.751.75
3, 5, 5, 3
6, 6, 6, 5
Poster
967 Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning5.005.750.75
6, 6, 3, 5
8, 6, 3, 6
Poster
968 Rethinking Supervised Pre-Training for Better Downstream Transferring5.005.750.75
5, 6, 3, 6
6, 6, 5, 6
Poster
969 Geometric Transformers for Protein Interface Contact Prediction5.005.750.75
6, 3, 6
6, 5, 6, 6
Poster
970 Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative6.255.75-0.50
5, 6, 6, 8
5, 6, 6, 6
Poster
971 Diverse Client Selection for Federated Learning via Submodular Maximization5.755.750.00
8, 6, 3, 6
8, 6, 3, 6
Poster
972 Neural Energy Minimization for Molecular Conformation Optimization4.255.751.50
6, 5, 3, 3
8, 6, 6, 3
Poster
973 Towards Continual Knowledge Learning of Language Models5.755.750.00
8, 6, 6, 3
8, 6, 6, 3
Poster
974 Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities5.005.750.75
6, 5, 3, 6
6, 5, 6, 6
Poster
975 KL Guided Domain Adaptation5.255.750.50
5, 8, 3, 5
6, 8, 3, 6
Poster
976 CodeTrek: Flexible Modeling of Code using an Extensible Relational Representation5.005.750.75
5, 5, 5, 5
5, 5, 5, 8
Poster
977 Generalized Demographic Parity for Group Fairness4.755.751.00
5, 6, 3, 5
5, 6, 6, 6
Poster
978 Evaluating Language-biased image classification based on semantic compositionality5.755.750.00
3, 8, 6, 6
3, 8, 6, 6
Poster
979 ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning5.755.750.00
6, 6, 6, 5
6, 6, 6, 5
Poster
980 Permutation Compressors for Provably Faster Distributed Nonconvex Optimization5.505.750.25
6, 5, 5, 6
6, 5, 6, 6
Poster
981 Distributionally Robust Fair Principal Components via Geodesic Descents5.755.750.00
6, 6, 6, 5
6, 6, 6, 5
Poster
982 DKM: Differentiable k-Means Clustering Layer for Neural Network Compression5.255.750.50
6, 6, 3, 6
6, 6, 5, 6
Poster
983 Variational Neural Cellular Automata4.755.751.00
5, 3, 6, 5
5, 5, 8, 5
Poster
984 On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning5.755.750.00
6, 5, 6, 6
6, 5, 6, 6
Poster
985 Towards Model Agnostic Federated Learning Using Knowledge Distillation5.255.750.50
3, 6, 6, 6
3, 8, 6, 6
Poster
986 Towards Building A Group-based Unsupervised Representation Disentanglement Framework5.505.750.25
6, 3, 5, 8
6, 3, 6, 8
Poster
987 Demystifying Limited Adversarial Transferability in Automatic Speech Recognition Systems5.755.750.00
5, 5, 5, 8
5, 5, 5, 8
Poster
988 Learning a subspace of policies for online adaptation in Reinforcement Learning5.005.750.75
6, 6, 5, 3
8, 6, 6, 3
Poster
989 Focus on the Common Good: Group Distributional Robustness Follows5.755.750.00
8, 6, 3, 6
8, 6, 3, 6
Poster
990 Adaptive Filters for Low-Latency and Memory-Efficient Graph Neural Networks5.755.750.00
8, 6, 6, 3
8, 6, 6, 3
Poster
991 GLASS: GNN with Labeling Tricks for Subgraph Representation Learning5.255.750.50
5, 5, 6, 5
5, 6, 6, 6
Poster
992 Data Poisoning Wonโ€™t Save You From Facial Recognition5.505.750.25
3, 6, 5, 8
1, 8, 6, 8
Poster
993 FILIP: Fine-grained Interactive Language-Image Pre-Training5.505.750.25
6, 5, 5, 6
6, 5, 6, 6
Poster
994 Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity5.255.750.50
5, 6, 5, 5
6, 6, 6, 5
Poster
995 Understanding approximate and unrolled dictionary learning for pattern recovery4.755.751.00
3, 3, 5, 8
3, 6, 6, 8
Poster
996 Variational oracle guiding for reinforcement learning5.505.750.25
8, 3, 6, 5
8, 3, 6, 6
Poster
997 HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning5.505.750.25
5, 8, 3, 6
6, 8, 3, 6
Poster
998 Towards Distribution Shift of Node-Level Prediction on Graphs: An Invariance Perspective4.755.751.00
3, 6, 5, 5
5, 6, 6, 6
Poster
999 Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space5.755.750.00
6, 3, 8, 6
6, 3, 8, 6
Poster
1000 Optimization inspired Multi-Branch Equilibrium Models5.505.750.25
6, 5, 5, 6
6, 6, 5, 6
Poster
1001 Constrained Physical-Statistics Models for Dynamical System Identification and Prediction5.505.750.25
3, 8, 5, 6
3, 8, 6, 6
Poster
1002 Imitation Learning by Reinforcement Learning5.755.750.00
6, 6, 6, 5
6, 6, 6, 5
Poster
1003 Exploring extreme parameter compression for pre-trained language models4.755.751.00
5, 3, 5, 6
6, 6, 5, 6
Poster
1004 Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations6.505.75-0.75
8, 6, 6, 6
5, 6, 6, 6
Poster
1005 On the Importance of Difficulty Calibration in Membership Inference Attacks5.755.750.00
5, 8, 5, 5
5, 8, 5, 5
Poster
1006 Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable4.675.751.08
5, 6, 3
6, 6, 5, 6
Poster
1007 Acceleration of Federated Learning with Alleviated Forgetting in Local Training5.255.750.50
5, 5, 5, 6
6, 6, 5, 6
Poster
1008 Learning Synthetic Environments and Reward Networks for Reinforcement Learning5.255.750.50
5, 3, 8, 5
6, 3, 8, 6
Poster
1009 Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach4.675.671.00
6, 5, 3
6, 5, 6
Poster
1010 Graph-Relational Domain Adaptation5.335.670.33
6, 5, 5
6, 5, 6
Poster
1011 Imitation Learning from Observations under Transition Model Disparity5.005.670.67
5, 5, 5
6, 6, 5
Poster
1012 Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty5.005.670.67
6, 3, 6
6, 5, 6
Poster
1013 ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity4.335.671.33
3, 5, 5
5, 6, 6
Poster
1014 EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression5.675.670.00
6, 3, 8
6, 3, 8
Poster
1015 Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming5.335.670.33
8, 5, 3
8, 6, 3
Poster
1016 Task Affinity with Maximum Bipartite Matching in Few-Shot Learning5.335.670.33
5, 8, 3
6, 8, 3
Poster
1017 Neural Spectral Marked Point Processes5.675.670.00
3, 8, 6
3, 8, 6
Poster
1018 Exploiting Class Activation Value for Partial-Label Learning5.335.670.33
3, 8, 5
3, 8, 6
Poster
1019 Towards Understanding the Data Dependency of Mixup-style Training5.675.670.00
6, 8, 3
6, 8, 3
Spotlight
1020 R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning5.675.670.00
6, 6, 5
6, 6, 5
Spotlight
1021 Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization5.675.670.00
6, 6, 5
6, 6, 5
Poster
1022 Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning5.205.600.40
6, 5, 5, 5, 5
6, 6, 5, 6, 5
Poster
1023 Graph Neural Network Guided Local Search for the Traveling Salesperson Problem5.405.600.20
3, 8, 5, 3, 8
3, 8, 6, 3, 8
Poster
1024 Plant 'n' Seek: Can You Find the Winning Ticket?4.805.600.80
3, 6, 5, 5, 5
5, 6, 6, 5, 6
Poster
1025 Pretrained Language Model in Continual Learning: A Comparative Study5.505.500.00
8, 6, 5, 3
8, 6, 5, 3
Poster
1026 Pre-training Molecular Graph Representation with 3D Geometry5.005.500.50
6, 6, 3, 5
6, 6, 5, 5
Poster
1027 Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing5.255.500.25
5, 3, 5, 8
6, 3, 5, 8
Poster
1028 COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks5.005.500.50
5, 3, 6, 6
5, 5, 6, 6
Poster
1029 Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions5.005.500.50
8, 3, 6, 3
8, 5, 6, 3
Poster
1030 PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks5.005.500.50
6, 5, 6, 3
6, 5, 6, 5
Poster
1031 Towards Evaluating the Robustness of Neural Networks Learned by Transduction5.255.500.25
5, 6, 5, 5
5, 6, 6, 5
Poster
1032 Attacking deep networks with surrogate-based adversarial black-box methods is easy5.255.500.25
5, 6, 5, 5
6, 6, 5, 5
Poster
1033 Crystal Diffusion Variational Autoencoder for Periodic Material Generation5.505.500.00
8, 5, 6, 3
8, 5, 6, 3
Poster
1034 New Insights on Reducing Abrupt Representation Change in Online Continual Learning5.505.500.00
3, 8, 6, 5
3, 8, 6, 5
Poster
1035 Object Pursuit: Building a Space of Objects via Discriminative Weight Generation5.255.500.25
5, 5, 6, 5
6, 5, 6, 5
Poster
1036 Learning State Representations via Retracing in Reinforcement Learning5.005.500.50
6, 5, 3, 6
8, 5, 3, 6
Poster
1037 Understanding and Leveraging Overparameterization in Recursive Value Estimation4.755.500.75
5, 3, 5, 6
5, 3, 6, 8
Poster
1038 The Role of Pretrained Representations for the OOD Generalization of RL Agents4.505.501.00
3, 3, 6, 6
5, 3, 6, 8
Poster
1039 Contrastive Learning is Just Meta-Learning5.505.500.00
6, 5, 5, 6
6, 5, 5, 6
Poster
1040 Non-Linear Operator Approximations for Initial Value Problems5.005.500.50
6, 5, 3, 6
8, 5, 3, 6
Poster
1041 Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation5.255.500.25
5, 6, 5, 5
5, 6, 6, 5
Poster
1042 Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How4.755.500.75
6, 3, 5, 5
6, 5, 5, 6
Poster
1043 Reducing the Communication Cost of Federated Learning through Multistage Optimization5.755.50-0.25
8, 5, 5, 5
6, 5, 5, 6
Poster
1044 Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs5.005.500.50
6, 6, 3, 5
6, 6, 5, 5
Poster
1045 Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations5.505.500.00
6, 5, 6, 5
6, 5, 6, 5
Poster
1046 Causal Contextual Bandits with Targeted Interventions5.505.500.00
5, 5, 6, 6
5, 5, 6, 6
Poster
1047 LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T55.005.500.50
3, 6, 6, 5
5, 6, 6, 5
Poster
1048 Stability Regularization for Discrete Representation Learning5.505.500.00
6, 6, 5, 5
6, 6, 5, 5
Poster
1049 Divergence-aware Federated Self-Supervised Learning5.005.500.50
5, 6, 6, 3
5, 8, 6, 3
Poster
1050 Learning to Guide and to be Guided in the Architect-Builder Problem5.505.500.00
5, 8, 6, 3
5, 8, 6, 3
Poster
1051 Dynamic Token Normalization improves Vision Transformers5.255.500.25
5, 6, 5, 5
6, 6, 5, 5
Poster
1052 Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer5.255.500.25
5, 5, 6, 5
5, 5, 6, 6
Poster
1053 ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models5.255.500.25
6, 5, 5, 5
6, 5, 6, 5
Poster
1054 Bayesian Neural Network Priors Revisited5.505.500.00
5, 8, 3, 6
5, 8, 3, 6
Poster
1055 Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation6.005.50-0.50
8, 6, 5, 5
8, 6, 5, 3
Poster
1056 Representation-Agnostic Shape Fields5.505.500.00
5, 6, 5, 6
5, 6, 5, 6
Poster
1057 Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions4.805.400.60
5, 6, 5, 3, 5
5, 6, 5, 5, 6
Poster
1058 Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs5.205.400.20
6, 3, 5, 6, 6
6, 3, 6, 6, 6
Poster
1059 Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning5.005.400.40
3, 3, 8, 5, 6
5, 5, 6, 5, 6
Poster
1060 Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate5.205.400.20
6, 5, 5, 5, 5
6, 6, 5, 5, 5
Poster
1061 Missingness Bias in Model Debugging5.335.330.00
5, 5, 6
5, 5, 6
Poster
1062 Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop5.335.330.00
8, 3, 5
8, 3, 5
Poster
1063 Fooling Explanations in Text Classifiers5.335.330.00
5, 6, 5
5, 6, 5
Poster
1064 ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods4.675.330.67
3, 5, 6
5, 5, 6
Poster
1065 Robust and Scalable SDE Learning: A Functional Perspective5.335.330.00
6, 5, 5
6, 5, 5
Poster
1066 AS-MLP: An Axial Shifted MLP Architecture for Vision5.005.330.33
5, 5, 5
5, 6, 5
Poster
1067 Zero-Shot Self-Supervised Learning for MRI Reconstruction5.335.330.00
5, 5, 6
5, 5, 6
Poster
1068 Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings5.255.250.00
5, 6, 5, 5
5, 6, 5, 5
Poster
1069 A fast and accurate splitting method for optimal transport: analysis and implementation5.255.250.00
6, 6, 6, 3
6, 6, 6, 3
Poster
1070 Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL5.005.250.25
6, 6, 3, 5
6, 6, 3, 6
Poster
1071 Visual hyperacuity with moving sensor and recurrent neural computations4.755.250.50
3, 3, 10, 3
3, 5, 10, 3
Poster
1072 Consistent Counterfactuals for Deep Models5.005.250.25
5, 3, 6, 6
6, 3, 6, 6
Poster
1073 Neural Network Approximation based on Hausdorff distance of Zonotopes5.255.250.00
6, 5, 5, 5
6, 5, 5, 5
Poster
1074 Practical Integration via Separable Bijective Networks5.005.250.25
5, 1, 6, 8
6, 1, 6, 8
Poster
1075 VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning5.005.250.25
3, 6, 6, 5
3, 6, 6, 6
Poster
1076 Maximizing Ensemble Diversity in Deep Reinforcement Learning5.005.250.25
5, 6, 6, 3
6, 6, 6, 3
Poster
1077 Memory Replay with Data Compression for Continual Learning5.255.250.00
6, 3, 6, 6
6, 3, 6, 6
Poster
1078 Model Agnostic Interpretability for Multiple Instance Learning3.505.251.75
3, 3, 3, 5
5, 5, 5, 6
Poster
1079 Towards General Function Approximation in Zero-Sum Markov Games5.255.250.00
6, 3, 6, 6
6, 3, 6, 6
Poster
1080 Visual Representation Learning over Latent Domains5.255.250.00
3, 6, 6, 6
3, 6, 6, 6
Poster
1081 Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning5.255.250.00
5, 5, 5, 6
5, 5, 5, 6
Poster
1082 Overcoming The Spectral Bias of Neural Value Approximation4.005.001.00
3, 6, 3
6, 6, 3
Poster
1083 FairCal: Fairness Calibration for Face Verification4.675.000.33
6, 5, 3
6, 6, 3
Poster
1084 CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing4.255.000.75
6, 5, 3, 3
6, 6, 5, 3
Poster
1085 Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization5.005.000.00
3, 8, 3, 6
3, 8, 3, 6
Poster
1086 Information Gain Propagation: a New Way to Graph Active Learning with Soft Labels5.505.00-0.50
3, 8, 5, 6
1, 8, 5, 6
Poster
1087 CoMPS: Continual Meta Policy Search4.805.000.20
3, 5, 8, 5, 3
3, 5, 6, 5, 6
Poster
1088 Learning Continuous Environment Fields via Implicit Functions5.005.000.00
1, 8, 6
1, 8, 6
Poster
1089 Towards Understanding Generalization via Decomposing Excess Risk Dynamics5.005.000.00
5, 5, 5, 5
5, 5, 5, 5
Poster
1090 Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation5.005.000.00
3, 6, 3, 8
3, 6, 3, 8
Oral
1091 ComPhy: Compositional Physical Reasoning of Objects and Events from Videos4.755.000.25
5, 3, 5, 6
5, 3, 6, 6
Poster
1092 Transformer Embeddings of Irregularly Spaced Events and Their Participants4.254.750.50
3, 3, 5, 6
3, 5, 5, 6
Poster
1093 Topologically Regularized Data Embeddings4.754.750.00
6, 5, 3, 5
6, 5, 3, 5
Poster
1094 Neural Program Synthesis with Query4.004.670.67
6, 3, 3
8, 3, 3
Poster
1095 Learning by Directional Gradient Descent4.004.500.50
1, 6, 3, 6
1, 6, 5, 6
Poster