AIConfPaper
← All conferences

ICML 2024 Accepted Papers

The full list of 2,610 papers accepted at ICML 2024 (International Conference on Machine Learning). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Poster: 2,275Spotlight: 191Oral: 144
  1. Stability and Generalization of Stochastic Compositional Gradient Descent AlgorithmsPoster2 citations
  2. Standardized Interpretable Fairness Measures for Continuous Risk ScoresPoster2 citations
  3. State-Constrained Zero-Sum Differential Games with One-Sided InformationPoster2 citations
  4. Stationary Latent Weight Inference for Unreliable Observations from Online Test-Time AdaptationPoster2 citations
  5. Statistical Inference Under Constrained Selection BiasPoster2 citations
  6. Stealthy Imitation: Reward-guided Environment-free Policy StealingPoster2 citations
  7. Stochastic Weakly Convex Optimization beyond Lipschitz ContinuityPoster2 citations
  8. StyDeSty: Min-Max Stylization and Destylization for Single Domain GeneralizationPoster2 citations
  9. Subhomogeneous Deep Equilibrium ModelsPoster2 citations
  10. Submodular framework for structured-sparse optimal transportPoster2 citations
  11. Supervised Matrix Factorization: Local Landscape Analysis and ApplicationsPoster2 citations
  12. Surprisingly Strong Performance Prediction with Neural Graph FeaturesPoster2 citations
  13. Tabular Insights, Visual Impacts: Transferring Expertise from Tables to ImagesSpotlight2 citations
  14. Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement LearningPoster2 citations
  15. The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free AlgorithmPoster2 citations
  16. The Merit of River Network Topology for Neural Flood ForecastingPoster2 citations
  17. To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DROPoster2 citations
  18. Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time OraclesPoster2 citations
  19. Transferring Knowledge From Large Foundation Models to Small Downstream ModelsPoster2 citations
  20. Transformers Get Stable: An End-to-End Signal Propagation Theory for Language ModelsPoster2 citations
  21. Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation LearningPoster2 citations
  22. Trust Regions for Explanations via Black-Box Probabilistic CertificationPoster2 citations
  23. Trustworthy Actionable PerturbationsPoster2 citations
  24. Two Tales of Single-Phase Contrastive Hebbian LearningPoster2 citations
  25. Two-Stage Shadow Inclusion Estimation: An IV Approach for Causal Inference under Latent Confounding and Collider BiasPoster2 citations
  26. UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEsPoster2 citations
  27. Understanding MLP-Mixer as a wide and sparse MLPPoster2 citations
  28. Understanding Stochastic Natural Gradient Variational InferencePoster2 citations
  29. Universal Gradient Methods for Stochastic Convex OptimizationPoster2 citations
  30. Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-trainingPoster2 citations
  31. Viewing Transformers Through the Lens of Long Convolutions LayersPoster2 citations
  32. WISER: Weak Supervision and Supervised Representation Learning to Improve Drug Response Prediction in CancerPoster2 citations
  33. Winner-takes-all learners are geometry-aware conditional density estimatorsPoster2 citations
  34. A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message PassingPoster1 citations
  35. A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPsPoster1 citations
  36. A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and FeedbackPoster1 citations
  37. ACPO: A Policy Optimization Algorithm for Average MDPs with ConstraintsPoster1 citations
  38. Activation-Descent Regularization for Input Optimization of ReLU NetworksPoster1 citations
  39. Adaptive Online Experimental Design for Causal DiscoverySpotlight1 citations
  40. Adaptive Stabilization Based on Machine Learning for Column GenerationPoster1 citations
  41. Adversarially Robust Hypothesis Transfer LearningPoster1 citations
  42. AegisFL: Efficient and Flexible Privacy-Preserving Byzantine-Robust Cross-silo Federated LearningPoster1 citations
  43. Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPsPoster1 citations
  44. Ai-sampler: Adversarial Learning of Markov kernels with involutive mapsPoster1 citations
  45. Algorithmic Stability Unleashed: Generalization Bounds with Unbounded LossesPoster1 citations
  46. Aligned Objective for Soft-Pseudo-Label Generation in Supervised LearningPoster1 citations
  47. An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural NetworksPoster1 citations
  48. An Information Theoretic Approach to Interaction-Grounded LearningPoster1 citations
  49. An Iterative Min-Min Optimization Method for Sparse Bayesian LearningPoster1 citations
  50. An Unsupervised Approach for Periodic Source Detection in Time SeriesPoster1 citations
  51. Automated Loss function Search for Class-imbalanced Node ClassificationPoster1 citations
  52. Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset SelectionPoster1 citations
  53. Best of Both Worlds Guarantees for Smoothed Online Quadratic OptimizationPoster1 citations
  54. Bifurcated Attention for Single-Context Large-Batch SamplingPoster1 citations
  55. Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised LearningPoster1 citations
  56. Bootstrapping Fisher Market Equilibrium and First-Price Pacing EquilibriumPoster1 citations
  57. Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic DataPoster1 citations
  58. Breaking through the learning plateaus of in-context learning in TransformerPoster1 citations
  59. Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer LearningSpotlight1 citations
  60. Bridging Environments and Language with Rendering Functions and Vision-Language ModelsPoster1 citations
  61. Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity LearningPoster1 citations
  62. Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst KernelPoster1 citations
  63. ByMI: Byzantine Machine Identification with False Discovery Rate ControlPoster1 citations
  64. CW Complex Hypothesis for Image DataPoster1 citations
  65. Calibration Bottleneck: Over-compressed Representations are Less CalibratablePoster1 citations
  66. Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?Poster1 citations
  67. Can Machines Learn the True Probabilities?Poster1 citations
  68. Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown MarginalsPoster1 citations
  69. Causal Discovery via Conditional Independence Testing with Proxy VariablesPoster1 citations
  70. Causal Discovery with Fewer Conditional Independence TestsPoster1 citations
  71. Causal Effect Identification in LiNGAM Models with Latent ConfoundersPoster1 citations
  72. Centralized Selection with Preferences in the Presence of BiasesPoster1 citations
  73. Characterizing ResNet's Universal Approximation CapabilityPoster1 citations
  74. Cluster-Aware Similarity Diffusion for Instance RetrievalPoster1 citations
  75. Coarse-To-Fine Tensor Trains for Compact Visual RepresentationsPoster1 citations
  76. CogDPM: Diffusion Probabilistic Models via Cognitive Predictive CodingPoster1 citations
  77. Collaborative Learning with Different Labeling FunctionsPoster1 citations
  78. Combining Experimental and Historical Data for Policy EvaluationPoster1 citations
  79. Compact Optimality Verification for Optimization ProxiesPoster1 citations
  80. Conditional Common Entropy for Instrumental Variable Testing and Partial IdentificationPoster1 citations
  81. Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular RepresentationsPoster1 citations
  82. Configurable Mirror Descent: Towards a Unification of Decision MakingPoster1 citations
  83. Consistent Submodular MaximizationPoster1 citations
  84. Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin DynamicsPoster1 citations
  85. Contamination-Resilient Anomaly Detection via Adversarial Learning on Partially-Observed Normal and Anomalous DataPoster1 citations
  86. Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal PointPoster1 citations
  87. Criterion Collapse and Loss Distribution ControlPoster1 citations
  88. DMTG: One-Shot Differentiable Multi-Task GroupingPoster1 citations
  89. Data-free Neural Representation Compression with Riemannian Neural DynamicsOral1 citations
  90. Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary DynamicsPoster1 citations
  91. Decoupling Feature Extraction and Classification Layers for Calibrated Neural NetworksPoster1 citations
  92. Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single DemonstrationPoster1 citations
  93. Deep Functional Factor Models: Forecasting High-Dimensional Functional Time Series via Bayesian Nonparametric FactorizationPoster1 citations
  94. Deep Stochastic MechanicsPoster1 citations
  95. Defining Neural Network Architecture through Polytope Structures of DatasetsSpotlight1 citations
  96. DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language ModelsPoster1 citations
  97. Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target DistributionPoster1 citations
  98. Differentially private exact recovery for stochastic block modelsPoster1 citations
  99. Diffuse, Sample, Project: Plug-And-Play Controllable Graph GenerationPoster1 citations
  100. Diffusion Rejection SamplingPoster1 citations
  101. Directly Denoising Diffusion ModelsPoster1 citations
  102. Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality FusionPoster1 citations
  103. Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support RecoverySpotlight1 citations
  104. Domain-wise Data Acquisition to Improve Performance under Distribution ShiftPoster1 citations
  105. Double-Step Alternating Extragradient with Increasing Timescale Separation for Finding Local Minimax Points: Provable ImprovementsPoster1 citations
  106. Dynamic Correlation Clustering in Sublinear Update TimeSpotlight1 citations
  107. Dynamic Spectral Clustering with Provable Approximation GuaranteePoster1 citations
  108. ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic AssistancePoster1 citations
  109. Easing Concept Bleeding in Diffusion via Entity Localization and AnchoringPoster1 citations
  110. Editing Partially Observable Networks via Graph Diffusion ModelsPoster1 citations
  111. Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and PlanningPoster1 citations
  112. Efficient Denoising Diffusion via Probabilistic MaskingPoster1 citations
  113. Efficient Online Set-valued Classification with Bandit FeedbackPoster1 citations
  114. Efficient Precision and Recall Metrics for Assessing Generative Models using Hubness-aware SamplingSpotlight1 citations
  115. Enhancing Implicit Shape Generators Using Topological RegularizationsPoster1 citations
  116. Enhancing Sufficient Dimension Reduction via Hellinger CorrelationPoster1 citations
  117. Enhancing Value Function Estimation through First-Order State-Action Dynamics in Offline Reinforcement LearningPoster1 citations
  118. Estimating Unknown Population Sizes Using the Hypergeometric DistributionSpotlight1 citations
  119. Evolving Subnetwork Training for Large Language ModelsPoster1 citations
  120. ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint ShrinkingOral1 citations
  121. Explain Temporal Black-Box Models via Functional DecompositionPoster1 citations
  122. Explaining Probabilistic Models with Distributional ValuesSpotlight1 citations
  123. Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial MonitoringPoster1 citations
  124. FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group FramesSpotlight1 citations
  125. FESSNC: Fast Exponentially Stable and Safe Neural ControllerPoster1 citations
  126. Factored-Reward Bandits with Intermediate ObservationsPoster1 citations
  127. Fast Algorithms for Hypergraph PageRank with Applications to Semi-Supervised LearningPoster1 citations
  128. Fast Text-to-3D-Aware Face Generation and Manipulation via Direct Cross-modal Mapping and Geometric RegularizationPoster1 citations
  129. Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and SketchingPoster1 citations
  130. Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous TrainingPoster1 citations
  131. Feature Importance Disparities for Data Bias InvestigationsPoster1 citations
  132. Few-shot Adaptation to Distribution Shifts By Mixing Source and Target EmbeddingsPoster1 citations
  133. Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement LearningPoster1 citations
  134. Forget Sharpness: Perturbed Forgetting of Model Biases Within SAM DynamicsPoster1 citations
  135. From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on NetworksPoster1 citations
  136. From Neurons to Neutrons: A Case Study in InterpretabilityPoster1 citations
  137. Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time GuaranteesPoster1 citations
  138. GATE: How to Keep Out Intrusive NeighborsPoster1 citations
  139. GFlowNet Training by Policy GradientsPoster1 citations
  140. GenCO: Generating Diverse Designs with Combinatorial ConstraintsPoster1 citations
  141. Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity AnalysisPoster1 citations
  142. Generalizing Orthogonalization for Models with Non-LinearitiesPoster1 citations
  143. Generative Conditional Distributions by Neural (Entropic) Optimal TransportPoster1 citations
  144. Generative Marginalization ModelsPoster1 citations
  145. Geometric Active Exploration in Markov Decision Processes: the Benefit of AbstractionPoster1 citations
  146. Gibbs Sampling of Continuous Potentials on a Quantum ComputerPoster1 citations
  147. Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer SamplesPoster1 citations
  148. HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention NetworkPoster1 citations
  149. Hierarchical Integral Probability Metrics: A distance on random probability measures with low sample complexityPoster1 citations
  150. How Does Goal Relabeling Improve Sample Efficiency?Poster1 citations
  151. IM-Unpack: Training and Inference with Arbitrarily Low Precision IntegersPoster1 citations
  152. IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptationPoster1 citations
  153. Identification and Estimation for Nonignorable Missing Data: A Data Fusion ApproachPoster1 citations
  154. Implicit Representations via Operator LearningPoster1 citations
  155. Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness RequirementsPoster1 citations
  156. Improving Robustness to Multiple Spurious Correlations by Multi-Objective OptimizationPoster1 citations
  157. Improving SAM Requires Rethinking its Optimization FormulationPoster1 citations
  158. Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov GamesPoster1 citations
  159. Incorporating Information into Shapley Values: Reweighting via a Maximum Entropy ApproachPoster1 citations
  160. Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement LearningPoster1 citations
  161. Individual Fairness in Graph DecompositionSpotlight1 citations
  162. Individualized Privacy Accounting via Subsampling with Applications in Combinatorial OptimizationPoster1 citations
  163. Inexact Newton-type Methods for Optimisation with Nonnegativity ConstraintsPoster1 citations
  164. Information-Directed Pessimism for Offline Reinforcement LearningPoster1 citations
  165. Interacting Diffusion Processes for Event Sequence ForecastingPoster1 citations
  166. InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature InterpretationSpotlight1 citations
  167. Kepler codebookPoster1 citations
  168. Kernel-Based Evaluation of Conditional Biological Sequence ModelsPoster1 citations
  169. LAGMA: LAtent Goal-guided Multi-Agent Reinforcement LearningPoster1 citations
  170. LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different ViewsPoster1 citations
  171. LPGD: A General Framework for Backpropagation through Embedded Optimization LayersPoster1 citations
  172. Langevin Policy for Safe Reinforcement LearningPoster1 citations
  173. Latent variable model for high-dimensional point process with structured missingnessPoster1 citations
  174. Learning 1-Bit Tiny Object Detector with Discriminative Feature RefinementPoster1 citations
  175. Learning Decision Policies with Instrumental Variables through Double Machine LearningPoster1 citations
  176. Learning Graph Representation via Graph Entropy MaximizationPoster1 citations
  177. Learning High-Frequency Functions Made Easy with Sinusoidal Positional EncodingPoster1 citations
  178. Learning Latent Space Hierarchical EBM Diffusion ModelsPoster1 citations
  179. Learning the Target Network in Function SpacePoster1 citations
  180. Lie Neurons: Adjoint-Equivariant Neural Networks for Semisimple Lie AlgebrasPoster1 citations
  181. Lightweight Image Super-Resolution via Flexible Meta PruningPoster1 citations
  182. Limited Preference Aided Imitation Learning from Imperfect DemonstrationsPoster1 citations
  183. Listening to the noise: Blind Denoising with Gibbs DiffusionPoster1 citations
  184. Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous TransformerPoster1 citations
  185. MLI Formula: A Nearly Scale-Invariant Solution with Noise PerturbationPoster1 citations
  186. MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited DataPoster1 citations
  187. Major-Minor Mean Field Multi-Agent Reinforcement LearningPoster1 citations
  188. Mean Field Langevin Actor-Critic: Faster Convergence and Global Optimality beyond Lazy LearningPoster1 citations
  189. Measuring Stochastic Data Complexity with Boltzmann Influence FunctionsPoster1 citations
  190. Meta Evidential Transformer for Few-Shot Open-Set RecognitionPoster1 citations
  191. Mimicking Better by Matching the Approximate Action DistributionPoster1 citations
  192. Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and ValuePoster1 citations
  193. Minimum Norm Interpolation Meets The Local Theory of Banach SpacesPoster1 citations
  194. Mitigating Privacy Risk in Membership Inference by Convex-Concave LossPoster1 citations
  195. Model-Based Minimum Bayes Risk Decoding for Text GenerationPoster1 citations
  196. Model-based Reinforcement Learning for Confounded POMDPsPoster1 citations
  197. Monotone Individual FairnessPoster1 citations
  198. Multi-View Clustering by Inter-cluster Connectivity Guided RewardPoster1 citations
  199. Multi-group Learning for Hierarchical GroupsPoster1 citations
  200. Multigroup RobustnessPoster1 citations
  201. Multiply-Robust Causal Change AttributionPoster1 citations
  202. Naive Bayes Classifiers over Missing Data: Decision and PoisoningPoster1 citations
  203. Navigating Scaling Laws: Compute Optimality in Adaptive Model TrainingSpotlight1 citations
  204. Nearest Neighbour Score Estimators for Diffusion Generative ModelsPoster1 citations
  205. Network Tight Community DetectionPoster1 citations
  206. Neural NeRF CompressionPoster1 citations
  207. NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator PriorsPoster1 citations
  208. New Sample Complexity Bounds for Sample Average Approximation in Heavy-Tailed Stochastic ProgrammingPoster1 citations
  209. No Dimensional Sampling Coresets for ClassificationSpotlight1 citations
  210. No Double Descent in Principal Component Regression: A High-Dimensional AnalysisPoster1 citations
  211. O$n$ Learning Deep O($n$)-Equivariant HyperspheresPoster1 citations
  212. Observable Propagation: Uncovering Feature Vectors in TransformersPoster1 citations
  213. Offline Imitation from Observation via Primal Wasserstein State Occupancy MatchingPoster1 citations
  214. On Convergence of Incremental Gradient for Non-convex Smooth FunctionsPoster1 citations
  215. On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-boxPoster1 citations
  216. On Multi-Armed Bandit with Impatient ArmsPoster1 citations
  217. On Online Experimentation without Device IdentifiersPoster1 citations
  218. On Stronger Computational Separations Between Multimodal and Unimodal Machine LearningSpotlight1 citations
  219. On Universally Optimal Algorithms for A/B TestingPoster1 citations
  220. On the Effectiveness of Supervision in Asymmetric Non-Contrastive LearningPoster1 citations
  221. On the Recoverability of Causal Relations from Temporally Aggregated I.I.D. DataPoster1 citations
  222. On the Role of Edge Dependency in Graph Generative ModelsPoster1 citations
  223. On the Weight Dynamics of Deep Normalized NetworksPoster1 citations
  224. Online Isolation ForestPoster1 citations
  225. Online Learning in Betting Markets: Profit versus PredictionPoster1 citations
  226. Online Learning with Bounded RecallPoster1 citations
  227. Online Matching with Stochastic Rewards: Provable Better Bound via Adversarial Reinforcement LearningOral1 citations
  228. Online Resource Allocation with Non-Stationary CustomersPoster1 citations
  229. Operator SVD with Neural Networks via Nested Low-Rank ApproximationPoster1 citations
  230. Optimal Coresets for Low-Dimensional Geometric MedianPoster1 citations
  231. Optimal Kernel Quantile Learning with Random FeaturesSpotlight1 citations
  232. Optimally Improving Cooperative Learning in a Social SettingPoster1 citations
  233. Optimistic Multi-Agent Policy GradientPoster1 citations
  234. Optimization without Retraction on the Random Generalized Stiefel ManifoldPoster1 citations
  235. Out of the Ordinary: Spectrally Adapting Regression for Covariate ShiftPoster1 citations
  236. PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space ModelsPoster1 citations
  237. Parameter Estimation in DAGs from Incomplete Data via Optimal TransportPoster1 citations
  238. Partially Stochastic Infinitely Deep Bayesian Neural NetworksPoster1 citations
  239. PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPRPoster1 citations
  240. Performance Bounds for Active Binary Testing with Information MaximizationPoster1 citations
  241. PinNet: Pinpoint Instructive Information for Retrieval Augmented Code-to-Text GenerationPoster1 citations
  242. PointMC: Multi-instance Point Cloud Registration based on Maximal CliquesPoster1 citations
  243. Position: AI/ML Influencers Have a Place in the Academic ProcessPoster1 citations
  244. Position: Data-driven Discovery with Large Generative ModelsPoster1 citations
  245. Position: Embracing Negative Results in Machine LearningOral1 citations
  246. Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AIPoster1 citations
  247. Position: Intent-aligned AI Systems Must Optimize for Agency PreservationSpotlight1 citations
  248. Position: Is machine learning good or bad for the natural sciences?Poster1 citations
  249. Position: Opportunities Exist for Machine Learning in Magnetic Fusion EnergyOral1 citations
  250. Precise Accuracy / Robustness Tradeoffs in Regression: Case of General NormsPoster1 citations
  251. Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural NetworksPoster1 citations
  252. Prediction Accuracy of Learning in Games : Follow-the-Regularized-Leader meets HeisenbergPoster1 citations
  253. Predictive Performance Comparison of Decision Policies Under ConfoundingPoster1 citations
  254. Preventing Model Collapse in Gaussian Process Latent Variable ModelsPoster1 citations
  255. Principled Gradient-Based MCMC for Conditional Sampling of TextPoster1 citations
  256. Privacy Profiles for Private SelectionPoster1 citations
  257. Private Truly-Everlasting Robust-PredictionOral1 citations
  258. Privately Learning Smooth Distributions on the Hypercube by ProjectionsPoster1 citations
  259. Probabilistic Conceptual Explainers: Trustworthy Conceptual Explanations for Vision Foundation ModelsPoster1 citations
  260. Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate PredictionsPoster1 citations
  261. Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical GuidelinesPoster1 citations
  262. Promoting External and Internal Equities Under Ex-Ante/Ex-Post Metrics in Online Resource AllocationSpotlight1 citations
  263. Provable Benefits of Local Steps in Heterogeneous Federated Learning for Neural Networks: A Feature Learning PerspectivePoster1 citations
  264. Provable Interactive Learning with Hindsight Instruction FeedbackPoster1 citations
  265. Provably Efficient Long-Horizon Exploration in Monte Carlo Tree Search through State Occupancy RegularizationPoster1 citations
  266. Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight ObservationPoster1 citations
  267. Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain AdaptationPoster1 citations
  268. Quantum Algorithm for Online Exp-concave OptimizationPoster1 citations
  269. REMEDI: Corrective Transformations for Improved Neural Entropy EstimationPoster1 citations
  270. RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement LearningPoster1 citations
  271. Random Latent Exploration for Deep Reinforcement LearningPoster1 citations
  272. Randomized Confidence Bounds for Stochastic Partial MonitoringPoster1 citations
  273. Rapid Learning without Catastrophic Forgetting in the Morris Water MazePoster1 citations
  274. Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing BackpropagationPoster1 citations
  275. Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery PerspectivePoster1 citations
  276. Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization ForecastPoster1 citations
  277. Rethinking DP-SGD in Discrete Domain: Exploring Logistic Distribution in the Realm of signSGDPoster1 citations
  278. Revisit the Essence of Distilling Knowledge through CalibrationPoster1 citations
  279. Reward-Free Kernel-Based Reinforcement LearningPoster1 citations
  280. Reweighted Solutions for Weighted Low Rank ApproximationPoster1 citations
  281. Riemannian Accelerated Zeroth-order Algorithm: Improved Robustness and Lower Query ComplexityPoster1 citations
  282. Risk Aware Benchmarking of Large Language ModelsPoster1 citations
  283. SFC: Achieve Accurate Fast Convolution under Low-precision ArithmeticPoster1 citations
  284. SPADE: Sparsity-Guided Debugging for Deep Neural NetworksPoster1 citations
  285. Safe Reinforcement Learning using Finite-Horizon Gradient-based EstimationPoster1 citations
  286. Sampling-based Multi-dimensional RecalibrationPoster1 citations
  287. Scale-Free Image Keypoints Using Differentiable Persistent HomologyPoster1 citations
  288. Scribble-Supervised Semantic Segmentation with Prototype-based Feature AugmentationPoster1 citations
  289. Self-Supervised Coarsening of Unstructured Grid with Automatic DifferentiationPoster1 citations
  290. Self-Supervised Interpretable End-to-End Learning via Latent Functional ModularityPoster1 citations
  291. Sequence Compression Speeds Up Credit Assignment in Reinforcement LearningPoster1 citations
  292. Simplicity Bias via Global Convergence of Sharpness MinimizationPoster1 citations
  293. Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At OncePoster1 citations
  294. Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal InitializationPoster1 citations
  295. Spectral Phase Transition and Optimal PCA in Block-Structured Spiked ModelsPoster1 citations
  296. Speech Self-Supervised Learning Using Diffusion Model Synthetic DataOral1 citations
  297. Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation ProcessPoster1 citations
  298. Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical DistributionPoster1 citations
  299. StrWAEs to Invariant RepresentationsPoster1 citations
  300. Straight-Through Meets Sparse Recovery: the Support Exploration AlgorithmPoster1 citations
  301. SuDA: Support-based Domain Adaptation for Sim2Real Hinge Joint Tracking with Flexible SensorsPoster1 citations
  302. Successor Features for Efficient Multi-Subject Controlled Text GenerationPoster1 citations
  303. Switched Flow Matching: Eliminating Singularities via Switching ODEsPoster1 citations
  304. TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic RegressionPoster1 citations
  305. The Computational Complexity of Finding Second-Order Stationary PointsPoster1 citations
  306. The Fundamental Limits of Least-Privilege LearningPoster1 citations
  307. The Non-linear $F$-Design and Applications to Interactive LearningPoster1 citations
  308. Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution LearnabilityOral1 citations
  309. Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural NetworksPoster1 citations
  310. To the Max: Reinventing Reward in Reinforcement LearningPoster1 citations
  311. Total Variation Floodgate for Variable Importance Inference in ClassificationPoster1 citations
  312. Toward Availability Attacks in 3D Point CloudsPoster1 citations
  313. Towards Interpretable Deep Local Learning with Successive Gradient ReconciliationPoster1 citations
  314. Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorOral1 citations
  315. Towards Realistic Model Selection for Semi-supervised LearningPoster1 citations
  316. Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random FeaturesPoster1 citations
  317. Towards Unified Multi-granularity Text Detection with Interactive AttentionSpotlight1 citations
  318. Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial ObfuscationPoster1 citations
  319. Transitional Uncertainty with Layered Intermediate PredictionsPoster1 citations
  320. Transport of Algebraic Structure to Latent EmbeddingsSpotlight1 citations
  321. Triple Changes Estimator for Targeted PoliciesSpotlight1 citations
  322. Turnstile $\ell_p$ leverage score sampling with applicationsPoster1 citations
  323. Unbiased Multi-Label Learning from Crowdsourced AnnotationsPoster1 citations
  324. Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client ParticipationPoster1 citations
  325. Understanding the Impact of Introducing Constraints at Inference Time on Generalization ErrorPoster1 citations
  326. Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function ClassesPoster1 citations
  327. Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex EigenvaluesPoster1 citations
  328. Unsupervised Episode Generation for Graph Meta-learningPoster1 citations
  329. VNN: Verification-Friendly Neural Networks with Hard Robustness GuaranteesPoster1 citations
  330. Variational Inference with Coverage Guarantees in Simulation-Based InferencePoster1 citations
  331. What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian BenchmarksPoster1 citations
  332. Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning ApproachPoster1 citations
  333. Zeroth-Order Methods for Constrained Nonconvex Nonsmooth Stochastic OptimizationOral1 citations
  334. convSeq: Fast and Scalable Method for Detecting Patterns in Spike DataPoster1 citations
  335. $\bf{\Phi}_\textrm{Flow}$: Differentiable Simulations for PyTorch, TensorFlow and JaxPoster
  336. $\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-ExpertsPoster
  337. A Bayesian Approach to Online PlanningPoster
  338. A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative ModelsPoster
  339. A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional OptimizationPoster
  340. A Dynamic Algorithm for Weighted Submodular Cover ProblemOral
  341. A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC MaximizationPoster
  342. A Fine-grained Analysis of Fitted Q-evaluation: Beyond Parametric ModelsPoster
  343. A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector NetworksPoster
  344. A General Online Algorithm for Optimizing Complex Performance MetricsPoster
  345. A Neural-Preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary ConditionsPoster
  346. A Single-Loop Robust Policy Gradient Method for Robust Markov Decision ProcessesPoster
  347. A Statistical Framework for Data-dependent Retrieval-Augmented ModelsPoster
  348. A Subquadratic Time Algorithm for Robust Sparse Mean EstimationSpotlight
  349. A Tensor Decomposition Perspective on Second-order RNNsSpotlight
  350. A Theory of Fault-Tolerant LearningSpotlight
  351. A Unified View of FANOVA: A Comprehensive Bayesian Framework for Component Selection and EstimationPoster
  352. A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order OraclesPoster
  353. Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State SpacesPoster
  354. Accelerating Convergence in Bayesian Few-Shot ClassificationPoster
  355. Acquisition Conditioned Oracle for Nongreedy Active Feature AcquisitionPoster
  356. Active Ranking and Matchmaking, with Perfect MatchingsPoster
  357. Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor ControlPoster
  358. Adaptive Group Personalization for Federated Mutual Transfer LearningPoster
  359. Adaptive Hierarchical Certification for Segmentation using Randomized SmoothingPoster
  360. Adaptive Robust Learning using Latent Bernoulli VariablesPoster
  361. Adaptively Learning to Select-Rank in Online PlatformsPoster
  362. Agnostic Interactive Imitation Learning: New Theory and Practical AlgorithmsPoster
  363. Agnostic Learning of Mixed Linear Regressions with EM and AM AlgorithmsPoster
  364. An Efficient Self-Learning Framework For Interactive Spoken Dialog SystemsPoster
  365. An Infinite-Width Analysis on the Jacobian-Regularised Training of a Neural NetworkPoster
  366. An Intrinsic Vector Heat NetworkPoster
  367. Analyzing $D^\alpha$ seeding for $k$-meansPoster
  368. Applying language models to algebraic topology: generating simplicial cycles using multi-labeling in Wu's formulaPoster
  369. Asymptotically Optimal and Computationally Efficient Average Treatment Effect Estimation in A/B testingPoster
  370. Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction GamesPoster
  371. Augmenting Decision with Hypothesis in Reinforcement LearningPoster
  372. Autoencoding Conditional Neural Processes for Representation LearningPoster
  373. Batch Singular Value Polarization and Weighted Semantic Augmentation for Universal Domain AdaptationPoster
  374. Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion ModelsPoster
  375. Bayesian Program Learning by Decompiling Amortized KnowledgePoster
  376. Bayesian Regret Minimization in Offline BanditsPoster
  377. BeigeMaps: Behavioral Eigenmaps for Reinforcement Learning from ImagesPoster
  378. Benchmarking Deletion Metrics with the Principled ExplanationsPoster
  379. Beyond the Norms: Detecting Prediction Errors in Regression ModelsSpotlight
  380. Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural NetworksPoster
  381. Bipartite Matching in Massive Graphs: A Tight Analysis of EDCSPoster
  382. Bootstrap AutoEncoders With Contrastive Paradigm for Self-supervised Gaze EstimationPoster
  383. Boundary Exploration for Bayesian Optimization With Unknown Physical ConstraintsPoster
  384. Box Facets and Cut Facets of Lifted Multicut PolytopesPoster
  385. Building Socially-Equitable Public ModelsPoster
  386. CF-OPT: Counterfactual Explanations for Structured PredictionPoster
  387. Careful with that Scalpel: Improving Gradient Surgery with an EMAPoster
  388. Category-Aware Active Domain AdaptationPoster
  389. Causal Customer Churn Analysis with Low-rank Tensor Block Hazard ModelPoster
  390. Causal Inference from Competing TreatmentsPoster
  391. Causal Inference out of Control: Estimating Performativity without Treatment RandomizationPoster
  392. Compositional Curvature Bounds for Deep Neural NetworksPoster
  393. Compress Clean Signal from Noisy Raw Image: A Self-Supervised ApproachPoster
  394. Concentration Inequalities for General Functions of Heavy-Tailed Random VariablesSpotlight
  395. Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data AugmentationPoster
  396. Conformal Predictions under Markovian DataPoster
  397. Consistent Adversarially Robust Linear Classification: Non-Parametric SettingPoster
  398. Convergence Guarantees for the DeepWalk Embedding on Block ModelsPoster
  399. Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization AlgorithmsPoster
  400. Convergence of Some Convex Message Passing Algorithms to a Fixed PointSpotlight
  401. Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain StimulationPoster
  402. Copula-Nested Spectral Kernel NetworkPoster
  403. Coresets for Multiple $\ell_p$ RegressionPoster
  404. Correlation-Induced Label Prior for Semi-Supervised Multi-Label LearningPoster
  405. DFD: Distilling the Feature Disparity Differently for DetectorsPoster
  406. DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform GenerationPoster
  407. DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric EstimationPoster
  408. DNCs Require More Planning StepsPoster
  409. Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition NumbersPoster
  410. Deconstructing the Goldilocks Zone of Neural Network InitializationPoster
  411. Degeneration-free Policy Optimization: RL Fine-Tuning for Language Models without DegenerationPoster
  412. Deletion-Anticipative Data Selection with a Limited BudgetPoster
  413. Demystifying SGD with Doubly Stochastic GradientsPoster
  414. Density Ratio Estimation with Doubly Strong RobustnessPoster
  415. Detecting Influence Structures in Multi-Agent Reinforcement LearningPoster
  416. Differentiable Combinatorial Scheduling at ScalePoster
  417. Differentially Private Domain Adaptation with Theoretical GuaranteesPoster
  418. Differentially Private Sum-Product NetworksPoster
  419. Discovering Features with Synergistic Interactions in Multiple ViewsPoster
  420. Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order GradientSpotlight
  421. Dynamic Metric Embedding into lp SpacePoster
  422. EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global ConvergencePoster
  423. Effective Federated Graph MatchingPoster
  424. Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior SamplingPoster
  425. Embarrassingly Parallel GFlowNetsPoster
  426. Enabling Few-Shot Learning with PID Control: A Layer Adaptive OptimizerPoster
  427. Energy-Efficient Gaussian Processes Using Low-Precision ArithmeticPoster
  428. Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement LearningPoster
  429. Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment ProblemPoster
  430. Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance ReductionPoster
  431. Estimating the Permanent by Nesting Importance SamplingPoster
  432. Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention TransformersPoster
  433. Expert Proximity as Surrogate Rewards for Single Demonstration Imitation LearningPoster
  434. Exploring Intrinsic Dimension for Vision-Language Model PruningPoster
  435. Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial ProblemsSpotlight
  436. Fair Classification with Partial Feedback: An Exploration-Based Data Collection ApproachPoster
  437. Fast Sampling-Based Sketches for TensorsSpotlight
  438. Fast White-Box Adversarial Streaming Without a Random OraclePoster
  439. Faster Adaptive Decentralized Learning AlgorithmsSpotlight
  440. Faster Streaming and Scalable Algorithms for Finding Directed Dense Subgraphs in Large GraphsPoster
  441. Federated Self-Explaining GNNs with Anti-shortcut AugmentationsPoster
  442. Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-AttentionPoster
  443. Finite Smoothing Algorithm for High-Dimensional Support Vector Machines and Quantile RegressionPoster
  444. Finite Time Logarithmic Regret Bounds for Self-Tuning RegulationPoster
  445. Foundations of Testing for Finite-Sample Causal DiscoveryPoster
  446. From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased DecisionsPoster
  447. Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication ConstraintsPoster
  448. Geometry-Aware Instrumental Variable RegressionPoster
  449. Hierarchical Novelty Detection via Fine-Grained Evidence AllocationPoster
  450. High-Dimensional Geometric Streaming for Nearly Low Rank DataPoster
  451. High-Order Contrastive Learning with Fine-grained Comparative Levels for Sparse Ordinal Tensor CompletionPoster
  452. High-Performance Temporal Reversible Spiking Neural Networks with $\mathcal{O}(L)$ Training Memory and $\mathcal{O}(1)$ Inference CostSpotlight
  453. Hybrid Reinforcement Learning from Offline Observation AlonePoster
  454. I/O Complexity of Attention, or How Optimal is FlashAttention?Oral
  455. Implicit Bias of AdamW: $\ell_\infty$-Norm Constrained OptimizationPoster
  456. Implicit Regularization in Feedback Alignment Learning Mechanisms for Neural NetworksPoster
  457. Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level PrivacyPoster
  458. Improved Dimensionality Dependence for Zeroth-Order Optimisation over Cross-PolytopesPoster
  459. Improved Modelling of Federated Datasets using Mixtures-of-Dirichlet-MultinomialsPoster
  460. Improving Computational Complexity in Statistical Models with Local Curvature InformationPoster
  461. Improving Generalization in Offline Reinforcement Learning via Adversarial Data SplittingPoster
  462. Improving Instruction Following in Language Models through Proxy-Based Uncertainty EstimationPoster
  463. Improving Sharpness-Aware Minimization by LookaheadPoster
  464. Incorporating probabilistic domain knowledge into deep multiple instance learningPoster
  465. Interplay of ROC and Precision-Recall AUCs: Theoretical Limits and Practical Implications in Binary ClassificationPoster
  466. Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN ModelsPoster
  467. Invariant Risk Minimization Is A Total Variation ModelPoster
  468. Is Kernel Prediction More Powerful than Gating in Convolutional Neural Networks?Poster
  469. Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMsPoster
  470. Keep the Momentum: Conservation Laws beyond Euclidean Gradient FlowsPoster
  471. Knowledge Distillation with Auxiliary VariablePoster
  472. LIDAO: Towards Limited Interventions for Debiasing (Large) Language ModelsSpotlight
  473. Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic ProgrammingPoster
  474. LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned ProportionsPoster
  475. Learning Causal Relations from Subsampled Time Series with Two Time-SlicesSpotlight
  476. Learning Divergence Fields for Shift-Robust Graph RepresentationsPoster
  477. Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational AutoencodersPoster
  478. Learning Mixtures of Gaussian Processes through Random ProjectionPoster
  479. Learning Multiple Secrets in MastermindPoster
  480. Learning Optimal Projection for Forecast Reconciliation of Hierarchical Time SeriesPoster
  481. Learning in Deep Factor Graphs with Gaussian Belief PropagationPoster
  482. Learning to Compile Programs to Neural NetworksPoster
  483. Learning to Explore for Stochastic Gradient MCMCPoster
  484. Learning-Rate-Free Stochastic Optimization over Riemannian ManifoldsSpotlight
  485. Leverage Class-Specific Accuracy to Guide Data Generation for Improving Image ClassificationPoster
  486. Leveraging Attractor Dynamics in Spatial Navigation for Better Language ParsingSpotlight
  487. Logistic Variational Bayes RevisitedPoster
  488. MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go ApproximationPoster
  489. MF-CLR: Multi-Frequency Contrastive Learning Representation for Time SeriesPoster
  490. MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-ResolutionPoster
  491. MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic PerspectivePoster
  492. Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous GamesPoster
  493. Matroid Semi-Bandits in Sublinear TimePoster
  494. Mean-field Chaos Diffusion ModelsOral
  495. Measures of diversity and space-filling designs for categorical dataPoster
  496. Modeling Language Tokens as Functionals of Semantic FieldsPoster
  497. Mollification Effects of Policy Gradient MethodsPoster
  498. MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology GenerationOral
  499. Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation LearningOral
  500. Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural NetworksPoster
  501. Neural Tangent Kernels for Axis-Aligned Tree EnsemblesPoster
  502. Neuro-Visualizer: A Novel Auto-Encoder-Based Loss Landscape Visualization Method With an Application in Knowledge-Guided Machine LearningPoster
  503. Neuroexplicit Diffusion Models for Inpainting of Optical Flow FieldsPoster
  504. Non-parametric Online Change Point Detection on Riemannian ManifoldsPoster
  505. Novel Spectral Algorithms for the Partial Credit ModelSpotlight
  506. OSN: Infinite Representations of Dynamic 3D Scenes from Monocular VideosPoster
  507. On Statistical Learning Theory for Distributional InputsPoster
  508. On the Consistency of Kernel Methods with Dependent ObservationsPoster
  509. On the Convergence of Projected Bures-Wasserstein Gradient Descent under Euclidean Strong ConvexityPoster
  510. On the Feasibility of Single-Pass Full-Capacity Learning in Linear Threshold Neurons with Binary Input VectorsPoster
  511. On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean FunctionsPoster
  512. Online Adaptive Anomaly Thresholding with Confidence SequencesPoster
  513. Open-Domain Text Evaluation via Contrastive Distribution MethodsPoster
  514. Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional NetworksPoster
  515. Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentationPoster
  516. Orthogonal Bootstrap: Efficient Simulation of Input UncertaintyPoster
  517. Overcoming the Optimizer's Curse: Obtaining Realistic Prescriptions from Neural NetworksPoster
  518. PairNet: Training with Observed Pairs to Estimate Individual Treatment EffectPoster
  519. Parallelized Spatiotemporal Slot Binding for VideosPoster
  520. Parameter-Dependent Competitive Analysis for Online Capacitated Coverage Maximization through Boostings and AttenuationsPoster
  521. Partial Optimality in the Linear Ordering ProblemPoster
  522. Perturb-and-Project: Differentially Private Similarities and MarginalsSpotlight
  523. Planning, Fast and Slow: Online Reinforcement Learning with Action-Free Offline Data via Multiscale PlannersPoster
  524. Polynomial-based Self-Attention for Table Representation LearningPoster
  525. Position: $C^*$-Algebraic Machine Learning $-$ Moving in a New DirectionPoster
  526. Position: A Roadmap to Pluralistic AlignmentPoster
  527. Position: Do Not Explain Vision Models Without ContextPoster
  528. Position: Machine Learning-powered Assessments of the EU Digital Services Act Aid Quantify Policy Impacts on Online HarmsPoster
  529. Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AIPoster
  530. Position: The Reasonable Person Standard for AIPoster
  531. Practical Hamiltonian Monte Carlo on Riemannian Manifolds via Relativity TheoryPoster
  532. Practical Performance Guarantees for Pipelined DNN InferenceSpotlight
  533. Predicting Dose-Response Curves with Deep Neural NetworksPoster
  534. Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized SystemsPoster
  535. Proactive DP: A Multiple Target Optimization Framework for DP-SGDPoster
  536. Profile Reconstruction from Private SketchesPoster
  537. Prompt-based Visual Alignment for Zero-shot Policy TransferPoster
  538. Provably Scalable Black-Box Variational Inference with Structured Variational FamiliesPoster
  539. PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial ConsistencyPoster
  540. Pursuing Overall Welfare in Federated Learning through Sequential Decision MakingPoster
  541. QBMK: Quantum-based Matching Kernels for Un-attributed GraphsSpotlight
  542. QORA: Zero-Shot Transfer via Interpretable Object-Relational Model LearningPoster
  543. RMIB: Representation Matching Information Bottleneck for Matching Text RepresentationsPoster
  544. ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation RatePoster
  545. Receptive Fields As Experts in Convolutional Neural ArchitecturesPoster
  546. Regression Learning with Limited Observations of Multivariate Outcomes and FeaturesPoster
  547. Regularized Q-learning through Robust AveragingPoster
  548. Reinforcement Learning and Regret Bounds for Admission ControlPoster
  549. Reinforcement Learning from Reachability Specifications: PAC Guarantees with Expected Conditional DistancePoster
  550. Reparameterized Importance Sampling for Robust Variational Bayesian Neural NetworksPoster
  551. Retrieval Across Any Domains via Large-scale Pre-trained ModelPoster
  552. Risk Estimation in a Markov Cost Process: Lower and Upper BoundsPoster
  553. Risk-Sensitive Policy Optimization via Predictive CVaR Policy GradientPoster
  554. Robust Inverse Graphics via Probabilistic InferencePoster
  555. Robust Sparse Estimation for Gaussians with Optimal Error under Huber ContaminationPoster
  556. SILVER: Single-loop variance reduction and application to federated learningPoster
  557. Safe Exploration in Dose Finding Clinical Trials with Heterogeneous ParticipantsPoster
  558. Sample Average Approximation for Conditional Stochastic Optimization with Dependent DataPoster
  559. Sample-Efficient Multiagent Reinforcement Learning with Reset ReplayPoster
  560. Scalable and Flexible Causal Discovery with an Efficient Test for AdjacencyPoster
  561. SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual DatasetsPoster
  562. Self-Rewarding Language ModelsPoster
  563. Sequential Kernel Goodness-of-fit TestingPoster
  564. Sharpness-Aware Data Generation for Zero-shot QuantizationPoster
  565. SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement LearningPoster
  566. Sign Rank Limitations for Inner Product Graph DecodersPoster
  567. Smooth Min-Max Monotonic NetworksPoster
  568. Sobolev Space Regularised Pre Density ModelsPoster
  569. Sparsest Models Elude Pruning: An Exposé of Pruning’s Current CapabilitiesPoster
  570. Spike Distance Function as a Learning Objective for Spike PredictionPoster
  571. Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model SplittingPoster
  572. Stability Evaluation through Distributional Perturbation AnalysisPoster
  573. Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to $K$-Level Stochastic OptimizationsPoster
  574. Stacking Deep Set Networks and Pooling by QuantilesPoster
  575. Stationarity without mean reversion in improper Gaussian processesPoster
  576. Stochastic Bandits with ReLU Neural NetworksPoster
  577. Stochastic Optimization with Arbitrary Recurrent Data SamplingPoster
  578. Studying K-FAC Heuristics by Viewing Adam through a Second-Order LensPoster
  579. Subequivariant Reinforcement Learning in 3D Multi-Entity Physical EnvironmentsPoster
  580. Switchable Decision: Dynamic Neural Generation NetworksPoster
  581. TVE: Learning Meta-attribution for Transferable Vision ExplainerPoster
  582. Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin RepresentationPoster
  583. Testing the Feasibility of Linear Programs with Bandit FeedbackSpotlight
  584. The Balanced-Pairwise-Affinities Feature TransformPoster
  585. The Effect of Weight Precision on the Neuron Count in Deep ReLU NetworksPoster
  586. The Role of Learning Algorithms in Collective ActionPoster
  587. Tight Partial Identification of Causal Effects with Marginal Distribution of Unmeasured ConfoundersSpotlight
  588. Tilt and Average : Geometric Adjustment of the Last Layer for RecalibrationPoster
  589. Tilt your Head: Activating the Hidden Spatial-Invariance of ClassifiersPoster
  590. Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable ComponentsPoster
  591. Towards Efficient Spiking Transformer: a Token Sparsification Framework for Training and Inference AccelerationPoster
  592. Towards Neural Architecture Search through Hierarchical Generative ModelingPoster
  593. Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random FeaturesSpotlight
  594. Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial OptimizationPoster
  595. Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and ConvergencePoster
  596. Tuning-free Estimation and Inference of Cumulative Distribution Function under Local Differential PrivacyPoster
  597. Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and RejectionPoster
  598. ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate SupervisionSpotlight
  599. USTAD: Unified Single-model Training Achieving Diverse Scores for Information RetrievalPoster
  600. Uncertainty-Aware Reward-Free Exploration with General Function ApproximationPoster
  601. Understanding the Training Speedup from Sampling with Approximate LossesPoster
  602. Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear RegressionPoster
  603. Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-ShiftsPoster
  604. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelPoster
  605. Visual Transformer with Differentiable Channel Selection: An Information Bottleneck Inspired ApproachPoster
  606. Weighted distance nearest neighbor condensingPoster
  607. When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal AbstractionsPoster
  608. When Will Gradient Regularization Be Harmful?Poster
  609. When is Transfer Learning Possible?Poster
  610. diff History for Neural Language AgentsPoster

ICML accepted papers in other years

ICML 2026 (6,634)ICML 2025 (3,333)ICML 2023 (1,828)ICML 2022 (1,228)ICML 2021 (1,181)ICML 2020 (1,082)ICML 2019 (773)ICML 2018 (620)ICML 2017 (433)ICML 2016 (322)ICML 2015 (270)

Looking for submission deadlines instead? See the conference deadline calendar.

ICML 2024 Accepted Papers · Full List of 2,610 Papers