ICML 2023 Accepted Papers

The full list of 1,828 papers accepted at ICML 2023 (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.

1. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsPoster5,839 citations
2. Robust Speech Recognition via Large-Scale Weak SupervisionPoster4,570 citations
3. PaLM-E: An Embodied Multimodal Language ModelPoster1,902 citations
4. Pythia: A Suite for Analyzing Large Language Models Across Training and ScalingOral1,168 citations
5. Consistency ModelsPoster1,000 citations
6. SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language ModelsPoster985 citations
7. PAL: Program-aided Language ModelsPoster849 citations
8. A Watermark for Large Language ModelsOral758 citations
9. The Flan Collection: Designing Data and Methods for Effective Instruction TuningPoster752 citations
10. SparseGPT: Massive Language Models Can be Accurately Pruned in One-ShotOral689 citations
11. DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability CurvatureOral664 citations
12. AudioLDM: Text-to-Audio Generation with Latent Diffusion ModelsPoster650 citations
13. Scaling Vision Transformers to 22 Billion ParametersOral650 citations
14. Fast Inference from Transformers via Speculative DecodingOral588 citations
15. Muse: Text-To-Image Generation via Masked Generative TransformersPoster572 citations
16. Transformers Learn In-Context by Gradient DescentOral523 citations
17. Cross-Entropy Loss Functions: Theoretical Analysis and ApplicationsPoster516 citations
18. Large Language Models Struggle to Learn Long-Tail KnowledgePoster511 citations
19. Scaling Laws for Reward Model OveroptimizationPoster489 citations
20. Whose Opinions Do Language Models Reflect?Oral470 citations
21. Large Language Models Can Be Easily Distracted by Irrelevant ContextPoster469 citations
22. Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject StudiesOral454 citations
23. FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPUOral421 citations
24. Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion ModelsPoster378 citations
25. Hyena Hierarchy: Towards Larger Convolutional Language ModelsOral347 citations
26. BEATs: Audio Pre-Training with Acoustic TokenizersOral341 citations
27. ClimaX: A foundation model for weather and climatePoster331 citations
28. TabDDPM: Modelling Tabular Data with Diffusion ModelsPoster323 citations
29. Deja Vu: Contextual Sparsity for Efficient LLMs at Inference TimeOral310 citations
30. Prompting Large Language Model for Machine Translation: A Case StudyPoster309 citations
31. Pix2Struct: Screenshot Parsing as Pretraining for Visual Language UnderstandingOral295 citations
32. Resurrecting Recurrent Neural Networks for Long SequencesOral294 citations
33. Composer: Creative and Controllable Image Synthesis with Composable ConditionsPoster281 citations
34. MultiDiffusion: Fusing Diffusion Paths for Controlled Image GenerationPoster280 citations
35. Better Diffusion Models Further Improve Adversarial TrainingPoster276 citations
36. DS-1000: A Natural and Reliable Benchmark for Data Science Code GenerationPoster267 citations
37. simple diffusion: End-to-end diffusion for high resolution imagesPoster261 citations
38. StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image SynthesisOral259 citations
39. Specializing Smaller Language Models towards Multi-Step ReasoningOral250 citations
40. Guiding Pretraining in Reinforcement Learning with Large Language ModelsPoster241 citations
41. VectorMapNet: End-to-end Vectorized HD Map LearningPoster241 citations
42. SE(3) diffusion model with application to protein backbone generationPoster233 citations
43. LEVER: Learning to Verify Language-to-Code Generation with ExecutionPoster227 citations
44. Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise ComparisonsPoster224 citations
45. The case for 4-bit precision: k-bit Inference Scaling LawsPoster220 citations
46. Pretraining Language Models with Human PreferencesOral216 citations
47. Image Restoration with Mean-Reverting Stochastic Differential EquationsPoster206 citations
48. Poisoning Language Models During Instruction TuningPoster202 citations
49. Grounding Large Language Models in Interactive Environments with Online Reinforcement LearningPoster199 citations
50. I$^2$SB: Image-to-Image Schrödinger BridgePoster192 citations
51. Transformers as Algorithms: Generalization and Stability in In-context LearningPoster191 citations
52. Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness AssumptionsPoster182 citations
53. NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware DiffusionPoster182 citations
54. Efficient Online Reinforcement Learning with Offline DataPoster180 citations
55. Hiera: A Hierarchical Vision Transformer without the Bells-and-WhistlesOral180 citations
56. Automatically Auditing Large Language Models via Discrete OptimizationPoster177 citations
57. Geometric Latent Diffusion Models for 3D Molecule GenerationPoster177 citations
58. Global Context Vision TransformersPoster172 citations
59. GNOT: A General Neural Operator Transformer for Operator LearningPoster171 citations
60. One Transformer Fits All Distributions in Multi-Modal Diffusion at ScalePoster170 citations
61. SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic SegmentationPoster165 citations
62. Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCPoster162 citations
63. TRAK: Attributing Model Behavior at ScaleOral162 citations
64. Text-To-4D Dynamic Scene GenerationPoster160 citations
65. Retrieval-Augmented Multimodal Language ModelingPoster159 citations
66. On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and TopologyPoster158 citations
67. Scaling Up Dataset Distillation to ImageNet-1K with Constant MemoryPoster152 citations
68. Spherical Fourier Neural Operators: Learning Stable Dynamics on the SphereOral152 citations
69. Deep Graph Representation Learning and Optimization for Influence MaximizationPoster150 citations
70. mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and VideoPoster147 citations
71. Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the Machiavelli BenchmarkOral146 citations
72. Jump-Start Reinforcement LearningPoster145 citations
73. VIMA: Robot Manipulation with Multimodal PromptsPoster144 citations
74. Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional DataPoster142 citations
75. Exphormer: Sparse Transformers for GraphsPoster141 citations
76. Fast Sampling of Diffusion Models via Operator LearningPoster140 citations
77. Repository-Level Prompt Generation for Large Language Models of CodePoster136 citations
78. Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative PretrainingPoster134 citations
79. Multisample Flow Matching: Straightening Flows with Minibatch CouplingsPoster133 citations
80. Compositional Exemplars for In-context LearningPoster131 citations
81. Grounding Language Models to Images for Multimodal Inputs and OutputsPoster128 citations
82. Raising the Cost of Malicious AI-Powered Image EditingOral128 citations
83. Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial ExamplesOral127 citations
84. Interventional Causal Representation LearningOral127 citations
85. LIV: Language-Image Representations and Rewards for Robotic ControlPoster127 citations
86. Change is Hard: A Closer Look at Subpopulation ShiftPoster126 citations
87. Diffusion Models are Minimax Optimal Distribution EstimatorsOral122 citations
88. Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and LanguageOral120 citations
89. On Provable Copyright Protection for Generative ModelsPoster120 citations
90. On the Expressive Power of Geometric Graph Neural NetworksPoster120 citations
91. Cones: Concept Neurons in Diffusion Models for Customized GenerationOral119 citations
92. ProtST: Multi-Modality Learning of Protein Sequences and Biomedical TextsOral119 citations
93. Are Diffusion Models Vulnerable to Membership Inference Attacks?Poster118 citations
94. Scalable Adaptive Computation for Iterative GenerationPoster117 citations
95. Graph Inductive Biases in Transformers without Message PassingPoster116 citations
96. ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object NavigationPoster115 citations
97. Understanding Plasticity in Neural NetworksOral114 citations
98. Human-Timescale Adaptation in an Open-Ended Task SpaceOral111 citations
99. Looped Transformers as Programmable ComputersPoster110 citations
100. AdaptDiffuser: Diffusion Models as Adaptive Self-evolving PlannersOral109 citations
101. In or Out? Fixing ImageNet Out-of-Distribution Detection EvaluationPoster108 citations
102. A Generalization of ViT/MLP-Mixer to GraphsPoster107 citations
103. The Dormant Neuron Phenomenon in Deep Reinforcement LearningOral107 citations
104. Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language ModelsPoster105 citations
105. Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RLPoster104 citations
106. Scaling Laws for Generative Mixed-Modal Language ModelsPoster104 citations
107. Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci CurvaturePoster103 citations
108. CLUSTSEG: Clustering for Universal SegmentationPoster102 citations
109. Unifying Molecular and Textual Representations via Multi-task Language ModellingPoster102 citations
110. Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNsPoster101 citations
111. Refining Generative Process with Discriminator Guidance in Score-based Diffusion ModelsOral101 citations
112. Protecting Language Generation Models via Invisible WatermarkingPoster100 citations
113. CHiLS: Zero-Shot Image Classification with Hierarchical Label SetsPoster99 citations
114. Open-Vocabulary Universal Image Segmentation with MaskCLIPPoster97 citations
115. A Toy Model of Universality: Reverse Engineering how Networks Learn Group OperationsPoster96 citations
116. Bigger, Better, Faster: Human-level Atari with human-level efficiencyPoster96 citations
117. SinDDM: A Single Image Denoising Diffusion ModelPoster95 citations
118. Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World ModellingPoster93 citations
119. Domain Adaptation for Time Series Under Feature and Label ShiftsPoster92 citations
120. How Do Transformers Learn Topic Structure: Towards a Mechanistic UnderstandingPoster92 citations
121. Structure-informed Language Models Are Protein DesignersOral92 citations
122. Learning GFlowNets From Partial Episodes For Improved Convergence And StabilityOral91 citations
123. Less is More: Task-aware Layer-wise Distillation for Language Model CompressionPoster91 citations
124. LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse ApproximationPoster91 citations
125. A theory of continuous generative flow networksPoster90 citations
126. Learning-Rate-Free Learning by D-AdaptationOral90 citations
127. Personalized Subgraph Federated LearningPoster90 citations
128. RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their RankOral90 citations
129. Loss-Guided Diffusion Models for Plug-and-Play Controllable GenerationPoster89 citations
130. Revisiting Weighted Aggregation in Federated Learning with Neural NetworksPoster89 citations
131. A Kernel-Based View of Language Model Fine-TuningPoster88 citations
132. Coder Reviewer Reranking for Code GenerationPoster88 citations
133. Can Large Language Models Reason about Program Invariants?Poster87 citations
134. Cramming: Training a Language Model on a single GPU in one day.Poster87 citations
135. DRew: Dynamically Rewired Message Passing with DelayPoster87 citations
136. Linear Causal Disentanglement via InterventionsPoster87 citations
137. Aligning Language Models with Preferences through $f$-divergence MinimizationPoster86 citations
138. XTab: Cross-table Pretraining for Tabular TransformersPoster86 citations
139. CLIPood: Generalizing CLIP to Out-of-DistributionsPoster85 citations
140. The Unreasonable Effectiveness of Few-shot Learning for Machine TranslationPoster85 citations
141. Equivariance with Learned Canonicalization FunctionsPoster84 citations
142. FedDisco: Federated Learning with Discrepancy-Aware CollaborationPoster84 citations
143. Multi-Objective GFlowNetsPoster84 citations
144. Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot LearningPoster84 citations
145. Controlled Text Generation with Natural Language InstructionsPoster83 citations
146. Understanding Oversquashing in GNNs through the Lens of Effective ResistancePoster83 citations
147. A Fully First-Order Method for Stochastic Bilevel OptimizationOral82 citations
148. Probabilistic Concept Bottleneck ModelsPoster80 citations
149. Task-Specific Skill Localization in Fine-tuned Language ModelsPoster80 citations
150. IRNeXt: Rethinking Convolutional Network Design for Image RestorationPoster79 citations
151. Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue CloudsPoster78 citations
152. KDEformer: Accelerating Transformers via Kernel Density EstimationPoster78 citations
153. Model Ratatouille: Recycling Diverse Models for Out-of-Distribution GeneralizationPoster78 citations
154. Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-type SamplersPoster78 citations
155. How Does Information Bottleneck Help Deep Learning?Poster77 citations
156. LongCoder: A Long-Range Pre-trained Language Model for Code CompletionPoster77 citations
157. Constrained Decision Transformer for Offline Safe Reinforcement LearningPoster76 citations
158. Discover and Cure: Concept-aware Mitigation of Spurious CorrelationPoster76 citations
159. Exploring Chemical Space with Score-based Out-of-distribution GenerationPoster76 citations
160. DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug DesignPoster75 citations
161. Fourmer: An Efficient Global Modeling Paradigm for Image RestorationOral75 citations
162. Hyperbolic Image-text RepresentationsPoster75 citations
163. Provable Dynamic Fusion for Low-Quality Multimodal DataPoster75 citations
164. Equivariant Architectures for Learning in Deep Weight SpacesOral74 citations
165. CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsPoster72 citations
166. Language Instructed Reinforcement Learning for Human-AI CoordinationPoster72 citations
167. A Modern Look at the Relationship between Sharpness and GeneralizationPoster71 citations
168. Autoregressive Diffusion Model for Graph GenerationPoster71 citations
169. DDGR: Continual Learning with Deep Diffusion-based Generative ReplayPoster71 citations
170. Dropout Reduces UnderfittingPoster71 citations
171. Exploring the Benefits of Training Expert Language Models over Instruction TuningPoster71 citations
172. Stabilizing Transformer Training by Preventing Attention Entropy CollapsePoster71 citations
173. CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular SynthesisPoster70 citations
174. Efficient and Degree-Guided Graph Generation via Discrete Diffusion ModelingPoster70 citations
175. Hyperparameters in Reinforcement Learning and How To Tune ThemPoster70 citations
176. SinFusion: Training Diffusion Models on a Single Image or VideoPoster70 citations
177. A Closer Look at Few-shot Classification AgainPoster69 citations
178. A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman TestsPoster69 citations
179. Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) SamplingPoster69 citations
180. Towards Omni-generalizable Neural Methods for Vehicle Routing ProblemsPoster69 citations
181. Improving the Model Consistency of Decentralized Federated LearningPoster68 citations
182. GOAT: A Global Transformer on Large-scale GraphsPoster67 citations
183. Non-autoregressive Conditional Diffusion Models for Time Series PredictionPoster67 citations
184. Better Training of GFlowNets with Local Credit and Incomplete TrajectoriesPoster66 citations
185. Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement LearningPoster66 citations
186. Dink-Net: Neural Clustering on Large GraphsPoster66 citations
187. PFGM++: Unlocking the Potential of Physics-Inspired Generative ModelsPoster66 citations
188. Reconstructive Neuron Pruning for Backdoor DefensePoster66 citations
189. SGD with Large Step Sizes Learns Sparse FeaturesPoster66 citations
190. DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size SchedulePoster65 citations
191. Improved Online Conformal Prediction via Strongly Adaptive Online LearningPoster65 citations
192. FAENet: Frame Averaging Equivariant GNN for Materials ModelingPoster64 citations
193. Linkless Link Prediction via Relational DistillationPoster64 citations
194. Optimizing DDPM Sampling with Shortcut Fine-TuningPoster64 citations
195. Simple and Fast Group Robustness by Automatic Feature ReweightingPoster64 citations
196. The Price of Differential Privacy under Continual ObservationOral64 citations
197. Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human LanguagePoster63 citations
198. On the Connection Between MPNN and Graph TransformerPoster63 citations
199. Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision ProcessesPoster62 citations
200. Text Generation with Diffusion Language Models: A Pre-training Approach with Continuous Paragraph DenoisePoster62 citations
201. InGram: Inductive Knowledge Graph Embedding via Relation GraphsPoster61 citations
202. Input Perturbation Reduces Exposure Bias in Diffusion ModelsPoster61 citations
203. On Pitfalls of Test-Time AdaptationPoster61 citations
204. Simple Hardware-Efficient Long Convolutions for Sequence ModelingPoster61 citations
205. Differentially Private Optimization on Large Model at Small CostPoster60 citations
206. Generalization on the Unseen, Logic Reasoning and Degree CurriculumOral60 citations
207. On the Role of Attention in Prompt-tuningPoster60 citations
208. Towards Coherent Image Inpainting Using Denoising Diffusion Implicit ModelsPoster60 citations
209. Bag of Tricks for Training Data Extraction from Language ModelsPoster59 citations
210. Can Neural Network Memorization Be Localized?Poster59 citations
211. Controllability-Aware Unsupervised Skill DiscoveryPoster59 citations
212. Data Poisoning Attacks Against Multimodal EncodersPoster59 citations
213. End-to-End Full-Atom Antibody DesignPoster59 citations
214. Lifelong Language Pretraining with Distribution-Specialized ExpertsPoster59 citations
215. On Penalty-based Bilevel Gradient Descent MethodPoster59 citations
216. Cross-Modal Fine-Tuning: Align then RefineOral58 citations
217. Efficient Personalized Federated Learning via Sparse Model-AdaptationPoster58 citations
218. Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance ReductionPoster58 citations
219. High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded VariancePoster58 citations
220. MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RLPoster58 citations
221. Multi-View Masked World Models for Visual Robotic ManipulationPoster58 citations
222. PromptBoosting: Black-Box Text Classification with Ten Forward PassesPoster58 citations
223. Tighter Bounds on the Expressivity of Transformer EncodersPoster58 citations
224. Towards Understanding and Improving GFlowNet TrainingPoster58 citations
225. Beyond Homophily: Reconstructing Structure for Graph-agnostic ClusteringPoster57 citations
226. Fast Federated Machine Unlearning with Nonlinear Functional TheoryPoster57 citations
227. Dirichlet Diffusion Score Model for Biological Sequence GenerationPoster56 citations
228. Personalized Federated Learning with Inferred Collaboration GraphsPoster56 citations
229. Reflected Diffusion ModelsPoster56 citations
230. Revisiting Gradient Clipping: Stochastic bias and tight convergence guaranteesPoster56 citations
231. Learning Physical Models that Can Respect Conservation LawsPoster55 citations
232. On the Power of Foundation ModelsPoster55 citations
233. Theory on Forgetting and Generalization of Continual LearningPoster55 citations
234. Action Matching: Learning Stochastic Dynamics from SamplesPoster54 citations
235. Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong ConvexityPoster54 citations
236. Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth LandscapeOral54 citations
237. Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic EnvironmentsPoster54 citations
238. High Probability Convergence of Stochastic Gradient MethodsPoster54 citations
239. Mechanistic Mode ConnectivityPoster54 citations
240. Minimizing Trajectory Curvature of ODE-based Generative ModelsPoster54 citations
241. Multi-Modal Classifiers for Open-Vocabulary Object DetectionPoster54 citations
242. Personalized Federated Learning under Mixture of DistributionsPoster54 citations
243. Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized NetworksPoster54 citations
244. AdaNPC: Exploring Non-Parametric Classifier for Test-Time AdaptationPoster53 citations
245. Diffusion Models for Black-Box OptimizationPoster53 citations
246. Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone GraphsPoster53 citations
247. GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion RestorationOral53 citations
248. Invariance in Policy Optimisation and Partial Identifiability in Reward LearningPoster53 citations
249. Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight OptimizationPoster53 citations
250. Tractable Control for Autoregressive Language GenerationOral53 citations
251. Bayes-optimal Learning of Deep Random Networks of Extensive-widthOral52 citations
252. MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion GenerationPoster52 citations
253. Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language ModelsOral52 citations
254. Solving High-Dimensional PDEs with Latent Spectral ModelsPoster52 citations
255. Feature learning in deep classifiers through Intermediate Neural CollapsePoster51 citations
256. Masked Trajectory Models for Prediction, Representation, and ControlPoster51 citations
257. Path Neural Networks: Expressive and Accurate Graph Neural NetworksPoster51 citations
258. Text-To-Concept (and Back) via Cross-Model AlignmentPoster51 citations
259. The Wisdom of Hindsight Makes Language Models Better Instruction FollowersPoster51 citations
260. Understanding Int4 Quantization for Language Models: Latency Speedup, Composability, and Failure CasesPoster51 citations
261. Why Is Public Pretraining Necessary for Private Model Training?Poster51 citations
262. Bayesian Estimation of Differential PrivacyPoster50 citations
263. BiBench: Benchmarking and Analyzing Network BinarizationPoster50 citations
264. Deep Regression UnlearningPoster50 citations
265. Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and DetectionPoster50 citations
266. GFlowNet-EM for Learning Compositional Latent Variable ModelsPoster50 citations
267. Geometric Clifford Algebra NetworksPoster50 citations
268. On Uni-Modal Feature Learning in Supervised Multi-Modal LearningPoster50 citations
269. Propensity Matters: Measuring and Enhancing Balancing for RecommendationPoster50 citations
270. Sampling-Based Accuracy Testing of Posterior Estimators for General InferencePoster50 citations
271. Settling the Reward HypothesisOral50 citations
272. Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate PoliciesPoster50 citations
273. Benign Overfitting in Two-layer ReLU Convolutional Neural NetworksPoster49 citations
274. ChiPFormer: Transferable Chip Placement via Offline Decision TransformerPoster49 citations
275. CocktailSGD: Fine-tuning Foundation Models over 500Mbps NetworksPoster49 citations
276. Dataset Distillation with Convexified Implicit GradientsPoster49 citations
277. GeCoNeRF: Few-shot Neural Radiance Fields via Geometric ConsistencyPoster49 citations
278. Improving Visual Prompt Tuning for Self-supervised Vision TransformersPoster49 citations
279. Leveraging Offline Data in Online Reinforcement LearningPoster49 citations
280. On the Identifiability and Estimation of Causal Location-Scale Noise ModelsPoster49 citations
281. Reinforcement Learning from Passive Data via Latent IntentionsOral49 citations
282. Sequential Predictive Conformal Inference for Time SeriesPoster49 citations
283. TAN Without a Burn: Scaling Laws of DP-SGDPoster49 citations
284. Constrained Monotonic Neural NetworksPoster48 citations
285. Direct Parameterization of Lipschitz-Bounded Deep NetworksOral48 citations
286. Improving Expert Predictions with Conformal PredictionPoster48 citations
287. Learning Deep Time-index Models for Time Series ForecastingPoster48 citations
288. Neural Diffusion ProcessesPoster48 citations
289. Neural Inverse Operators for Solving PDE Inverse ProblemsPoster48 citations
290. Structural Re-weighting Improves Graph Domain AdaptationPoster48 citations
291. Transformers Meet Directed GraphsPoster48 citations
292. Unsupervised Out-of-Distribution Detection with Diffusion InpaintingPoster48 citations
293. A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image ModelsPoster47 citations
294. Architecture-Agnostic Masked Image Modeling -- From ViT back to CNNPoster47 citations
295. Equivariant Polynomials for Graph Neural NetworksOral47 citations
296. Identifiability of Label Noise Transition MatrixPoster47 citations
297. Model-Bellman Inconsistency for Model-based Offline Reinforcement LearningPoster47 citations
298. Uncertainty Estimation by Fisher Information-based Evidential Deep LearningPoster47 citations
299. Data Feedback Loops: Model-driven Amplification of Dataset BiasesOral46 citations
300. Efficient Approximations of Complete Interatomic Potentials for Crystal Property PredictionPoster46 citations
301. Fully-Adaptive Composition in Differential PrivacyPoster46 citations
302. The Benefits of Mixup for Feature LearningPoster46 citations
303. The Power of Preconditioning in Overparameterized Low-Rank Matrix SensingPoster46 citations
304. Achieving High Accuracy with PINNs via Energy Natural Gradient DescentPoster45 citations
305. Conformal Prediction Sets for Graph Neural NetworksPoster45 citations
306. Disentangled Multiplex Graph Representation LearningPoster45 citations
307. Forget Unlearning: Towards True Data-Deletion in Machine LearningPoster45 citations
308. Learnability and Algorithm for Continual LearningPoster45 citations
309. Mitigating Spurious Correlations in Multi-modal Models during Fine-tuningPoster45 citations
310. Synthetic Data, Real Errors: How (Not) to Publish and Use Synthetic DataPoster45 citations
311. Towards Understanding Generalization of Graph Neural NetworksPoster45 citations
312. Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree OptimizationPoster44 citations
313. Effective Neural Topic Modeling with Embedding Clustering RegularizationPoster44 citations
314. Fair and Optimal Classification via Post-ProcessingPoster44 citations
315. Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale LearningPoster44 citations
316. GREAD: Graph Neural Reaction-Diffusion NetworksPoster44 citations
317. HOPE: High-order Graph ODE For Modeling Interacting DynamicsPoster44 citations
318. Modeling Temporal Data as Continuous Functions with Stochastic Process DiffusionPoster44 citations
319. Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex ConversionPoster44 citations
320. X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionPoster44 citations
321. Forward-Backward Gaussian Variational Inference via JKO in the Bures-Wasserstein SpacePoster43 citations
322. POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained ModelsPoster43 citations
323. Revisiting Discriminative vs. Generative Classifiers: Theory and ImplicationsPoster43 citations
324. Tuning Computer Vision Models With Task RewardsPoster43 citations
325. A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal PretrainingPoster42 citations
326. An Investigation into Pre-Training Object-Centric Representations for Reinforcement LearningPoster42 citations
327. Dual Focal Loss for CalibrationPoster42 citations
328. Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex OptimizationPoster42 citations
329. Graph Neural Networks with Learnable and Optimal Polynomial BasesPoster42 citations
330. Hierarchical Diffusion for Offline Decision MakingPoster42 citations
331. Learning to Maximize Mutual Information for Dynamic Feature SelectionPoster42 citations
332. Neural networks trained with SGD learn distributions of increasing complexityPoster42 citations
333. Optimal Goal-Reaching Reinforcement Learning via Quasimetric LearningPoster42 citations
334. Shape-Guided Dual-Memory Learning for 3D Anomaly DetectionPoster42 citations
335. Spatial Implicit Neural Representations for Global-Scale Species MappingPoster42 citations
336. Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task LearningPoster42 citations
337. A Closer Look at Self-Supervised Lightweight Vision TransformersPoster41 citations
338. Adaptive Smoothing Gradient Learning for Spiking Neural NetworksPoster41 citations
339. Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data ValuePoster41 citations
340. Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing CorrectionOral41 citations
341. Group Equivariant Fourier Neural Operators for Partial Differential EquationsPoster41 citations
342. HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic EncryptionOral41 citations
343. InfoDiffusion: Representation Learning Using Information Maximizing Diffusion ModelsPoster41 citations
344. Multi-Epoch Matrix Factorization Mechanisms for Private Machine LearningOral41 citations
345. PFNs4BO: In-Context Learning for Bayesian OptimizationPoster41 citations
346. Prototype-Sample Relation Distillation: Towards Replay-Free Continual LearningPoster41 citations
347. The SSL Interplay: Augmentations, Inductive Bias, and GeneralizationPoster41 citations
348. Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix SensingPoster41 citations
349. Adversarial Policies Beat Superhuman Go AIsOral40 citations
350. Anti-Exploration by Random Network DistillationPoster40 citations
351. Causal Proxy Models for Concept-based Model ExplanationsPoster40 citations
352. High Fidelity Image Counterfactuals with Probabilistic Causal ModelsPoster40 citations
353. Learning Neural Constitutive Laws from Motion Observations for Generalizable PDE DynamicsPoster40 citations
354. OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic ModelsPoster40 citations
355. Provably Learning Object-Centric RepresentationsOral40 citations
356. Searching Large Neighborhoods for Integer Linear Programs with Contrastive LearningPoster40 citations
357. Topologically Faithful Image Segmentation via Induced Matching of Persistence BarcodesPoster40 citations
358. Towards Deep Attention in Graph Neural Networks: Problems and RemediesPoster40 citations
359. UPop: Unified and Progressive Pruning for Compressing Vision-Language TransformersPoster40 citations
360. Efficient Learning of Mesh-Based Physical Simulation with Bi-Stride Multi-Scale Graph Neural NetworkPoster39 citations
361. FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias ReductionPoster39 citations
362. From Robustness to Privacy and BackPoster39 citations
363. Generalized Teacher Forcing for Learning Chaotic DynamicsOral39 citations
364. Hierarchical Neural Coding for Controllable CAD Model GenerationPoster39 citations
365. Learning Subpocket Prototypes for Generalizable Structure-based Drug DesignPoster39 citations
366. On Second-Order Scoring Rules for Epistemic Uncertainty QuantificationPoster39 citations
367. On the Stepwise Nature of Self-Supervised LearningPoster39 citations
368. Oscillation-free Quantization for Low-bit Vision TransformersPoster39 citations
369. Parameter-Level Soft-Masking for Continual LearningPoster39 citations
370. Actor-Critic Alignment for Offline-to-Online Reinforcement LearningPoster38 citations
371. Deep Latent State Space Models for Time-Series GenerationPoster38 citations
372. Ewald-based Long-Range Message Passing for Molecular GraphsPoster38 citations
373. FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split ModelsPoster38 citations
374. How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk ControlPoster38 citations
375. In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect EstimationPoster38 citations
376. Mimetic Initialization of Self-Attention LayersOral38 citations
377. Robust Counterfactual Explanations for Neural Networks With Probabilistic GuaranteesPoster38 citations
378. Stochastic Gradient Descent under Markovian Sampling SchemesPoster38 citations
379. $\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task InterpolationPoster37 citations
380. Brainformers: Trading Simplicity for EfficiencyPoster37 citations
381. Conditional Graph Information Bottleneck for Molecular Relational LearningPoster37 citations
382. Improving Medical Predictions by Irregular Multimodal Electronic Health Records ModelingPoster37 citations
383. On the Convergence of Federated Averaging with Cyclic Client ParticipationPoster37 citations
384. Self-supervised learning of Split Invariant Equivariant representationsPoster37 citations
385. Towards Sustainable Learning: Coresets for Data-efficient Deep LearningPoster37 citations
386. A Closer Look at the Intervention Procedure of Concept Bottleneck ModelsPoster36 citations
387. Beyond Reward: Offline Preference-guided Policy OptimizationPoster36 citations
388. Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component AnalysisPoster36 citations
389. CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language ModelsPoster36 citations
390. Fractional Denoising for 3D Molecular Pre-trainingPoster36 citations
391. Generative Adversarial Symmetry DiscoveryPoster36 citations
392. Graph Mixup with Soft AlignmentsPoster36 citations
393. Minimax estimation of discontinuous optimal transport maps: The semi-discrete casePoster36 citations
394. Perturbation Analysis of Neural CollapsePoster36 citations
395. SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-EfficientPoster36 citations
396. WL meet VCPoster36 citations
397. Decentralized Stochastic Bilevel Optimization with Improved per-Iteration ComplexityPoster35 citations
398. Diffusion Based Representation LearningPoster35 citations
399. FlexRound: Learnable Rounding based on Element-wise Division for Post-Training QuantizationPoster35 citations
400. Image Shortcut Squeezing: Countering Perturbative Availability Poisons with CompressionPoster35 citations
401. Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEsPoster35 citations
402. Inverse Reinforcement Learning without Reinforcement LearningPoster35 citations
403. ODS: Test-Time Adaptation in the Presence of Open-World Data ShiftOral35 citations
404. Out-of-Distribution Generalization of Federated Learning via Implicit Invariant RelationshipsPoster35 citations
405. Policy Mirror Ascent for Efficient and Independent Learning in Mean Field GamesPoster35 citations
406. Quantifying the Knowledge in GNNs for Reliable Distillation into MLPsPoster35 citations
407. RLSbench: Domain Adaptation Under Relaxed Label ShiftPoster35 citations
408. Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear EstimationPoster34 citations
409. BPipe: Memory-Balanced Pipeline Parallelism for Training Large Language ModelsOral34 citations
410. Deterministic equivalent and error universality of deep random features learningPoster34 citations
411. Fast as CHITA: Neural Network Pruning with Combinatorial OptimizationPoster34 citations
412. Faster Rates of Convergence to Stationary Points in Differentially Private OptimizationPoster34 citations
413. Hidden Symmetries of ReLU NetworksPoster34 citations
414. HyperTuning: Toward Adapting Large Language Models without Back-propagationPoster34 citations
415. Hyperbolic Representation Learning: Revisiting and AdvancingPoster34 citations
416. ModelDiff: A Framework for Comparing Learning AlgorithmsPoster34 citations
417. Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced DataPoster34 citations
418. Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural NetworksOral34 citations
419. Polynomial Time and Private Learning of Unbounded Gaussian Mixture ModelsPoster34 citations
420. Towards Explaining Distribution ShiftsPoster34 citations
421. Understanding Self-Predictive Learning for Reinforcement LearningPoster34 citations
422. CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph ClassificationPoster33 citations
423. FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck EquationPoster33 citations
424. Implicit Neural Spatial Representations for Time-dependent PDEsPoster33 citations
425. Measuring the Impact of Programming Language DistributionPoster33 citations
426. Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series ImputationPoster33 citations
427. Scalable Multi-Agent Reinforcement Learning through Intelligent Information AggregationPoster33 citations
428. Scaling Laws for Multilingual Neural Machine TranslationPoster33 citations
429. Second-order regression models exhibit progressive sharpening to the edge of stabilityPoster33 citations
430. Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and VulnerabilityPoster33 citations
431. Trompt: Towards a Better Deep Neural Network for Tabular DataPoster33 citations
432. Constrained Efficient Global Optimization of Expensive Black-box FunctionsPoster32 citations
433. Efficiently predicting high resolution mass spectra with graph neural networksPoster32 citations
434. Mitigating Memorization of Noisy Labels by Clipping the Model PredictionPoster32 citations
435. Multicalibration as Boosting for RegressionOral32 citations
436. OpenFE: Automated Feature Generation with Expert-level PerformancePoster32 citations
437. Policy Regularization with Dataset Constraint for Offline Reinforcement LearningPoster32 citations
438. SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization ProblemsPoster32 citations
439. The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and BeyondPoster32 citations
440. The Ideal Continual Learner: An Agent That Never ForgetsPoster32 citations
441. Transformed Distribution Matching for Missing Value ImputationPoster32 citations
442. Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated LearningPoster31 citations
443. Differential Privacy has Bounded Impact on Fairness in ClassificationPoster31 citations
444. Half-Hop: A graph upsampling approach for slowing down message passingPoster31 citations
445. Improving Graph Neural Networks with Learnable Propagation OperatorsPoster31 citations
446. Invariant Slot Attention: Object Discovery with Slot-Centric Reference FramesPoster31 citations
447. Multi-channel Autobidding with Budget and ROI ConstraintsPoster31 citations
448. Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian MarginalsPoster31 citations
449. PLay: Parametrically Conditioned Layout Generation using Latent DiffusionPoster31 citations
450. QuantumDARTS: Differentiable Quantum Architecture Search for Variational Quantum AlgorithmsPoster31 citations
451. Sketching Meets Differential Privacy: Fast Algorithm for Dynamic Kronecker Projection MaintenancePoster31 citations
452. The Monge Gap: A Regularizer to Learn All Transport MapsPoster31 citations
453. Why do Nearest Neighbor Language Models Work?Poster31 citations
454. Cooperative Open-ended Learning Framework for Zero-Shot CoordinationPoster30 citations
455. Counterfactual Identifiability of Bijective Causal ModelsPoster30 citations
456. Deep Generative Symbolic Regression with Monte-Carlo-Tree-SearchPoster30 citations
457. Discrete Key-Value BottleneckPoster30 citations
458. Does a Neural Network Really Encode Symbolic Concepts?Poster30 citations
459. EF21-P and Friends: Improved Theoretical Communication Complexity for Distributed Optimization with Bidirectional CompressionPoster30 citations
460. LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated LearningPoster30 citations
461. Meta Optimal TransportPoster30 citations
462. Neural Algorithmic Reasoning with Causal RegularisationPoster30 citations
463. On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch BaselinePoster30 citations
464. Regret Minimization and Convergence to Equilibria in General-sum Markov GamesPoster30 citations
465. Temporally Consistent Transformers for Video GenerationPoster30 citations
466. "Why did the Model Fail?": Attributing Model Performance Changes to Distribution ShiftsPoster29 citations
467. Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?Poster29 citations
468. Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative ComonotonicityPoster29 citations
469. Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision ProcessesPoster29 citations
470. Distilling Internet-Scale Vision-Language Models into Embodied AgentsPoster29 citations
471. Featured Graph Coarsening with Similarity GuaranteesPoster29 citations
472. How Bad is Top-$K$ Recommendation under Competing Content Creators?Oral29 citations
473. Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood ModelsPoster29 citations
474. Learning Preconditioners for Conjugate Gradient PDE SolversPoster29 citations
475. Random Shuffle Transformer for Image RestorationPoster29 citations
476. Reprogramming Pretrained Language Models for Antibody Sequence InfillingPoster29 citations
477. Statistical Indistinguishability of Learning AlgorithmsPoster29 citations
478. What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?Poster29 citations
479. Efficient and Equivariant Graph Networks for Predicting Quantum HamiltonianPoster28 citations
480. Interpretable Neural-Symbolic Concept ReasoningPoster28 citations
481. Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise MappingOral28 citations
482. Overcoming Simplicity Bias in Deep Networks using a Feature SievePoster28 citations
483. Quantum Policy Gradient Algorithm with Optimized Action DecodingPoster28 citations
484. RSC: Accelerate Graph Neural Networks Training via Randomized Sparse ComputationsPoster28 citations
485. Robust Camera Pose Refinement for Multi-Resolution Hash EncodingPoster28 citations
486. SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine VariancePoster28 citations
487. Spatial-Temporal Graph Learning with Adversarial Contrastive AdaptationPoster28 citations
488. Statistical Foundations of Prior-Data Fitted NetworksPoster28 citations
489. Tighter Lower Bounds for Shuffling SGD: Random Permutations and BeyondOral28 citations
490. When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral AnalysisPoster28 citations
491. A Fast, Well-Founded Approximation to the Empirical Neural Tangent KernelPoster27 citations
492. A Unified Audio-Visual Learning Framework for Localization, Separation, and RecognitionPoster27 citations
493. B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden ConfoundingPoster27 citations
494. BiRT: Bio-inspired Replay in Vision Transformers for Continual LearningPoster27 citations
495. Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3DPoster27 citations
496. Compositional Score Modeling for Simulation-Based InferencePoster27 citations
497. Deep Laplacian-based Options for Temporally-Extended ExplorationPoster27 citations
498. Fast, Differentiable and Sparse Top-k: a Convex Analysis PerspectivePoster27 citations
499. Federated Adversarial Learning: A Framework with Convergence AnalysisPoster27 citations
500. Generalized Polyak Step Size for First Order Optimization with MomentumPoster27 citations
501. Internet Explorer: Targeted Representation Learning on the Open WebPoster27 citations
502. Learning in POMDPs is Sample-Efficient with Hindsight ObservabilityPoster27 citations
503. Modality-Agnostic Variational Compression of Implicit Neural RepresentationsPoster27 citations
504. Neural signature kernels as infinite-width-depth-limits of controlled ResNetsPoster27 citations
505. On the Privacy-Robustness-Utility Trilemma in Distributed LearningPoster27 citations
506. Pre-training for Speech Translation: CTC Meets Optimal TransportOral27 citations
507. Revisiting the Linear-Programming Framework for Offline RL with General Function ApproximationPoster27 citations
508. SEGA: Structural Entropy Guided Anchor View for Graph Contrastive LearningPoster27 citations
509. Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG SignalsPoster27 citations
510. Trustworthy Policy Learning under the Counterfactual No-Harm CriterionPoster27 citations
511. Algorithmic Stability of Heavy-Tailed SGD with General Loss FunctionsPoster26 citations
512. An SDE for Modeling SAM: Theory and InsightsPoster26 citations
513. Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural NetworksPoster26 citations
514. Emergent Agentic Transformer from Chain of Hindsight ExperiencePoster26 citations
515. Estimating the Contamination Factor's Distribution in Unsupervised Anomaly DetectionPoster26 citations
516. For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created EqualPoster26 citations
517. Future-conditioned Unsupervised Pretraining for Decision TransformerPoster26 citations
518. Generalizing Neural Wave FunctionsPoster26 citations
519. Hindsight Learning for MDPs with Exogenous InputsPoster26 citations
520. Learning Deductive Reasoning from Synthetic Corpus based on Formal LogicPoster26 citations
521. Off-Policy Evaluation for Large Action Spaces via Conjunct Effect ModelingPoster26 citations
522. On the Generalization of Multi-modal Contrastive LearningPoster26 citations
523. Online Learning in Stackelberg Games with an Omniscient FollowerPoster26 citations
524. Outline, Then Details: Syntactically Guided Coarse-To-Fine Code GenerationPoster26 citations
525. Prototype-oriented unsupervised anomaly detection for multivariate time seriesPoster26 citations
526. Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RLOral26 citations
527. The Numerical Stability of Hyperbolic Representation LearningPoster26 citations
528. Vertical Federated Graph Neural Network for Recommender SystemPoster26 citations
529. Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional InputPoster25 citations
530. Beyond Uniform Lipschitz Condition in Differentially Private OptimizationPoster25 citations
531. Constant Matters: Fine-grained Error Bound on Differentially Private Continual ObservationPoster25 citations
532. Distribution Free Prediction Sets for Node ClassificationPoster25 citations
533. Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio DetectionPoster25 citations
534. Federated Conformal Predictors for Distributed Uncertainty QuantificationPoster25 citations
535. From Hypergraph Energy Functions to Hypergraph Neural NetworksPoster25 citations
536. Long-Term Rhythmic Video SoundtrackerPoster25 citations
537. Mastering the Unsupervised Reinforcement Learning Benchmark from PixelsOral25 citations
538. Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept RehearsalPoster25 citations
539. Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature IndividualizationPoster25 citations
540. Optimal Rates and Efficient Algorithms for Online Bayesian PersuasionPoster25 citations
541. Optimizing the Collaboration Structure in Cross-Silo Federated LearningPoster25 citations
542. Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement LearningPoster25 citations
543. Out-of-Domain Robustness via Targeted AugmentationsPoster25 citations
544. Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task modelsPoster25 citations
545. PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture SearchPoster25 citations
546. Progressive Purification for Instance-Dependent Partial Label LearningPoster25 citations
547. Refined Regret for Adversarial MDPs with Linear Function ApproximationPoster25 citations
548. Sequential Kernelized Independence TestingPoster25 citations
549. Towards Theoretical Understanding of Inverse Reinforcement LearningOral25 citations
550. Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature SuppressionOral25 citations
551. Why Random Pruning Is All We Need to Start SparsePoster25 citations
552. A Unified Optimization Framework of ANN-SNN Conversion: Towards Optimal Mapping from Activation Values to Firing RatesPoster24 citations
553. Achieving Linear Speedup in Non-IID Federated Bilevel LearningPoster24 citations
554. Adversarial Cheap TalkPoster24 citations
555. An Effective Meaningful Way to Evaluate Survival ModelsPoster24 citations
556. Conformal Prediction with Missing ValuesPoster24 citations
557. Continual Learning in Linear Classification on Separable DataPoster24 citations
558. Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-ResolutionPoster24 citations
559. Curriculum Co-disentangled Representation Learning across Multiple Environments for Social RecommendationPoster24 citations
560. Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the LeastPoster24 citations
561. Detecting Out-of-distribution Data through In-distribution Class PriorPoster24 citations
562. Effective Structured Prompting by Meta-Learning and Representative VerbalizerPoster24 citations
563. Explaining Reinforcement Learning with Shapley ValuesPoster24 citations
564. FAIRER: Fairness as Decision Rationale AlignmentPoster24 citations
565. GFlowOut: Dropout with Generative Flow NetworksPoster24 citations
566. Generalization Bounds using Data-Dependent Fractal DimensionsPoster24 citations
567. Generative Pretraining for Black-Box OptimizationPoster24 citations
568. Identifying Interpretable Subspaces in Image RepresentationsPoster24 citations
569. LazyGNN: Large-Scale Graph Neural Networks via Lazy PropagationPoster24 citations
570. Learn to Accumulate Evidence from All Training Samples: Theory and PracticePoster24 citations
571. LinSATNet: The Positive Linear Satisfiability Neural NetworksPoster24 citations
572. Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth LabelsPoster24 citations
573. Moderately Distributional Exploration for Domain GeneralizationPoster24 citations
574. Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaRPoster24 citations
575. Policy Gradient in Robust MDPs with Global Convergence GuaranteePoster24 citations
576. Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous InputsPoster24 citations
577. QASA: Advanced Question Answering on Scientific ArticlesPoster24 citations
578. Rigid Body Flows for Sampling Molecular Crystal StructuresPoster24 citations
579. Semi-Supervised Offline Reinforcement Learning with Action-Free TrajectoriesPoster24 citations
580. Surrogate Module Learning: Reduce the Gradient Error Accumulation in Training Spiking Neural NetworksPoster24 citations
581. Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive AttributesPoster24 citations
582. Algorithmic Collective Action in Machine LearningPoster23 citations
583. Behavior Contrastive Learning for Unsupervised Skill DiscoveryPoster23 citations
584. Boosting Graph Contrastive Learning via Graph Contrastive SaliencyPoster23 citations
585. Continual Vision-Language Representation Learning with Off-Diagonal InformationPoster23 citations
586. Contrastive Learning Meets Homophily: Two Birds with One StonePoster23 citations
587. DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution ModelsPoster23 citations
588. Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation ScorePoster23 citations
589. Do Perceptually Aligned Gradients Imply Robustness?Oral23 citations
590. Feature Expansion for Graph Neural NetworksPoster23 citations
591. Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement LearningOral23 citations
592. GLOBE-CE: A Translation Based Approach for Global Counterfactual ExplanationsPoster23 citations
593. Graph Contrastive Backdoor AttacksPoster23 citations
594. Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large ModelsOral23 citations
595. Learning Neural PDE Solvers with Parameter-Guided Channel AttentionPoster23 citations
596. Men Also Do Laundry: Multi-Attribute Bias AmplificationPoster23 citations
597. On Strengthening and Defending Graph Reconstruction Attack with Markov Chain ApproximationPoster23 citations
598. Optimizing NOTEARS Objectives via Topological SwapsPoster23 citations
599. Probabilistic Imputation for Time-series Classification with Missing DataPoster23 citations
600. ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPsPoster23 citations
601. SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image TranslationPoster23 citations
602. The Acquisition of Physical Knowledge in Generative Neural NetworksPoster23 citations
603. The Benefits of Model-Based Generalization in Reinforcement LearningPoster23 citations
604. Two-Scale Gradient Descent Ascent Dynamics Finds Mixed Nash Equilibria of Continuous Games: A Mean-Field PerspectivePoster23 citations
605. What Can Be Learnt With Wide Convolutional Neural Networks?Poster23 citations
606. $H$-Consistency Bounds for Pairwise Misranking Loss SurrogatesPoster22 citations
607. A theory of representation learning gives a deep generalisation of kernel methodsPoster22 citations
608. Atari-5: Distilling the Arcade Learning Environment down to Five GamesPoster22 citations
609. Chemically Transferable Generative Backmapping of Coarse-Grained ProteinsPoster22 citations
610. Controllable Neural Symbolic RegressionPoster22 citations
611. Evolving Semantic Prototype Improves Generative Zero-Shot LearningPoster22 citations
612. Fast Rates for Maximum Entropy ExplorationPoster22 citations
613. From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural NetworksPoster22 citations
614. Graph Positional Encoding via Random Feature PropagationPoster22 citations
615. Improved Regret for Efficient Online Reinforcement Learning with Linear Function ApproximationPoster22 citations
616. IncDSI: Incrementally Updatable Document RetrievalPoster22 citations
617. Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement LearningPoster22 citations
618. LeadFL: Client Self-Defense against Model Poisoning in Federated LearningPoster22 citations
619. Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient ApproachPoster22 citations
620. MEWL: Few-shot multimodal word learning with referential uncertaintyPoster22 citations
621. MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural NetworksPoster22 citations
622. Optimal No-Regret Learning for One-Sided Lipschitz FunctionsPoster22 citations
623. Paging with Succinct PredictionsPoster22 citations
624. RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative EvolutionPoster22 citations
625. Rethinking Backdoor AttacksPoster22 citations
626. Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph MatchingPoster22 citations
627. Second-Order Optimization with Lazy HessiansOral22 citations
628. Stable Estimation of Heterogeneous Treatment EffectsPoster22 citations
629. Tighter Information-Theoretic Generalization Bounds from SupersamplesOral22 citations
630. Toward Large Kernel ModelsPoster22 citations
631. User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical SystemsPoster22 citations
632. Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over TimePoster21 citations
633. An Instrumental Variable Approach to Confounded Off-Policy EvaluationPoster21 citations
634. Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression: Fast Convergence and Partial ParticipationOral21 citations
635. Bi-directional Masks for Efficient N:M Sparse TrainingPoster21 citations
636. Bidirectional Learning for Offline Model-based Biological Sequence DesignPoster21 citations
637. Conformal Prediction for Federated Uncertainty Quantification Under Label ShiftPoster21 citations
638. Contextual Combinatorial Bandits with Probabilistically Triggered ArmsPoster21 citations
639. Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex OptimizationPoster21 citations
640. DevFormer: A Symmetric Transformer for Context-Aware Device PlacementPoster21 citations
641. Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation LearningPoster21 citations
642. Learning Perturbations to Explain Time Series PredictionsPoster21 citations
643. Learning useful representations for shifting tasks and distributionsPoster21 citations
644. Mu$^2$SLAM: Multitask, Multilingual Speech and Language ModelsOral21 citations
645. Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time SeriesOral21 citations
646. Neural Wasserstein Gradient Flows for Discrepancies with Riesz KernelsPoster21 citations
647. Node Embedding from Neural Hamiltonian Orbits in Graph Neural NetworksPoster21 citations
648. Omnipredictors for Constrained OptimizationPoster21 citations
649. On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain AdaptationPoster21 citations
650. On Kinetic Optimal Probability Paths for Generative ModelsPoster21 citations
651. On the Optimality of Misspecified Kernel Ridge RegressionPoster21 citations
652. On the Relationship Between Explanation and Prediction: A Causal ViewPoster21 citations
653. Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex OptimizationPoster21 citations
654. Performative Reinforcement LearningPoster21 citations
655. Predictive Flows for Faster Ford-FulkersonPoster21 citations
656. Quantum Speedups for Zero-Sum Games via Improved Dynamic Gibbs SamplingPoster21 citations
657. Retrosynthetic Planning with Dual Value NetworksPoster21 citations
658. SAM operates far from home: eigenvalue regularization as a dynamical phenomenonPoster21 citations
659. Streaming Active Learning with Deep Neural NetworksPoster21 citations
660. Towards Practical Preferential Bayesian Optimization with Skew Gaussian ProcessesPoster21 citations
661. Towards Reliable Neural SpecificationsOral21 citations
662. UMD: Unsupervised Model Detection for X2X Backdoor AttacksPoster21 citations
663. When is Realizability Sufficient for Off-Policy Reinforcement Learning?Poster21 citations
664. Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From FanoPoster20 citations
665. Anchor Sampling for Federated Learning with Partial Client ParticipationPoster20 citations
666. Attributing Image Generative Models using Latent FingerprintsPoster20 citations
667. Calibrating Multimodal LearningOral20 citations
668. Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?Poster20 citations
669. Denoising MCMC for Accelerating Diffusion-Based Generative ModelsOral20 citations
670. Distributional Offline Policy Evaluation with Predictive Error GuaranteesPoster20 citations
671. DoCoFL: Downlink Compression for Cross-Device Federated LearningPoster20 citations
672. FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic PlanningPoster20 citations
673. Generative Graph Dictionary LearningPoster20 citations
674. Gradient-Free Structured Pruning with Unlabeled DataPoster20 citations
675. Importance Weighted Expectation-Maximization for Protein Sequence DesignPoster20 citations
676. Improving Fair Training under Correlation ShiftsPoster20 citations
677. InfoOT: Information Maximizing Optimal TransportPoster20 citations
678. Learning to Bid in Repeated First-Price Auctions with BudgetsPoster20 citations
679. MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from ObservationsPoster20 citations
680. Momentum Ensures Convergence of SIGNSGD under Weaker AssumptionsPoster20 citations
681. Reinforcement Learning in Low-rank MDPs with Density FeaturesPoster20 citations
682. Safe Offline Reinforcement Learning with Real-Time Budget ConstraintsPoster20 citations
683. Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret MinimizationPoster20 citations
684. The Implicit Regularization of Dynamical Stability in Stochastic Gradient DescentPoster20 citations
685. A Game-Theoretic Framework for Managing Risk in Multi-Agent SystemsPoster19 citations
686. A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional LayerPoster19 citations
687. A Study of Global and Episodic Bonuses for Exploration in Contextual MDPsOral19 citations
688. A Theoretical Analysis of the Learning Dynamics under Class ImbalancePoster19 citations
689. AbODE: Ab initio antibody design using conjoined ODEsPoster19 citations
690. Blackout Diffusion: Generative Diffusion Models in Discrete-State SpacesPoster19 citations
691. Byzantine-Robust Learning on Heterogeneous Data via Gradient SplittingPoster19 citations
692. Does Continual Learning Equally Forget All Parameters?Poster19 citations
693. Effectively Using Public Data in Privacy Preserving Machine LearningPoster19 citations
694. Feature Directions Matter: Long-Tailed Learning via Rotated Balanced RepresentationPoster19 citations
695. Generating Private Synthetic Data with Genetic AlgorithmsPoster19 citations
696. Hierarchies of Reward MachinesOral19 citations
697. In Search for a Generalizable Method for Source Free Domain AdaptationPoster19 citations
698. Live in the Moment: Learning Dynamics Model Adapted to Evolving PolicyPoster19 citations
699. Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse MapsPoster19 citations
700. Normalizing Flows for Interventional Density EstimationPoster19 citations
701. Nugget: Neural Agglomerative Embeddings of TextPoster19 citations
702. One-Shot Federated Conformal PredictionPoster19 citations
703. Optimally-weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free InferencePoster19 citations
704. PAC-Bayesian Offline Contextual Bandits With GuaranteesPoster19 citations
705. Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action SpacePoster19 citations
706. Revisiting Simple Regret: Fast Rates for Returning a Good ArmPoster19 citations
707. Robust and Scalable Bayesian Online Changepoint DetectionPoster19 citations
708. Strategic Classification with Unknown User ManipulationsPoster19 citations
709. Towards Robust Graph Incremental Learning on Evolving GraphsPoster19 citations
710. Understanding and Generalizing Contrastive Learning from the Inverse Optimal Transport PerspectivePoster19 citations
711. Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse DataPoster19 citations
712. spred: Solving L1 Penalty with SGDPoster19 citations
713. A Neural PDE Solver with Temporal Stencil ModelingPoster18 citations
714. Adversarially Robust PAC Learnability of Real-Valued FunctionsPoster18 citations
715. Approximation Algorithms for Fair Range ClusteringPoster18 citations
716. Brauer's Group Equivariant Neural NetworksOral18 citations
717. Can Forward Gradient Match Backpropagation?Poster18 citations
718. Causal Discovery with Latent Confounders Based on Higher-Order CumulantsPoster18 citations
719. Causal Isotonic Calibration for Heterogeneous Treatment EffectsPoster18 citations
720. Conformal Inference is (almost) Free for Neural Networks Trained with Early StoppingPoster18 citations
721. Decentralized SGD and Average-direction SAM are Asymptotically EquivalentPoster18 citations
722. Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy AdaptationPoster18 citations
723. Distance Weighted Supervised Learning for Offline Interaction DataPoster18 citations
724. Federated Linear Contextual Bandits with User-level Differential PrivacyPoster18 citations
725. Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural NetworksPoster18 citations
726. Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and BeyondPoster18 citations
727. Hierarchical Programmatic Reinforcement Learning via Learning to Compose ProgramsPoster18 citations
728. Hypervolume Knowledge Gradient: A Lookahead Approach for Multi-Objective Bayesian Optimization with Partial InformationPoster18 citations
729. Lower Bounds for Learning in Revealing POMDPsPoster18 citations
730. Markovian Gaussian Process Variational AutoencodersPoster18 citations
731. Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal ApproximationPoster18 citations
732. NNSplitter: An Active Defense Solution for DNN Model via Automated Weight ObfuscationPoster18 citations
733. No One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server ComputationPoster18 citations
734. Patch-level Contrastive Learning via Positional Query for Visual Pre-trainingPoster18 citations
735. Revisiting Sampling for Combinatorial OptimizationPoster18 citations
736. Sequence Modeling with Multiresolution Convolutional MemoryPoster18 citations
737. Slot-VAE: Object-Centric Scene Generation with Slot AttentionPoster18 citations
738. System Identification of Neural Systems: If We Got It Right, Would We Know?Poster18 citations
739. TGRL: An Algorithm for Teacher Guided Reinforcement LearningPoster18 citations
740. Towards Trustworthy Explanation: On Causal RationalizationPoster18 citations
741. Vector Quantized Wasserstein Auto-EncoderPoster18 citations
742. Why does Throwing Away Data Improve Worst-Group Error?Oral18 citations
743. A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit FeedbackPoster17 citations
744. Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive ConceptsPoster17 citations
745. CLUTR: Curriculum Learning via Unsupervised Task Representation LearningPoster17 citations
746. Confidence and Dispersity Speak: Characterizing Prediction Matrix for Unsupervised Accuracy EstimationPoster17 citations
747. Curious Replay for Model-based AdaptationPoster17 citations
748. Distortion and Uncertainty Aware Loss for Panoramic Depth CompletionPoster17 citations
749. Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning AttacksPoster17 citations
750. Extrapolative Controlled Sequence Generation via Iterative RefinementPoster17 citations
751. GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer ProgrammingPoster17 citations
752. Gaussian Process Priors for Systems of Linear Partial Differential Equations with Constant CoefficientsOral17 citations
753. Graph Generative Model for Benchmarking Graph Neural NetworksPoster17 citations
754. Learning to Learn from APIs: Black-Box Data-Free Meta-LearningPoster17 citations
755. LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal ControlPoster17 citations
756. Minimalistic Predictions to Schedule Jobs with Online Precedence ConstraintsPoster17 citations
757. Robust Collaborative Learning with Linear Gradient OverheadPoster17 citations
758. Run-off Election: Improved Provable Defense against Data Poisoning AttacksPoster17 citations
759. SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement LearningPoster17 citations
760. Understanding the Complexity Gains of Single-Task RL with a CurriculumPoster17 citations
761. A Coupled Flow Approach to Imitation LearningPoster16 citations
762. Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point ProblemsPoster16 citations
763. Adapting to game trees in zero-sum imperfect information gamesOral16 citations
764. Adversarial Collaborative Learning on Non-IID FeaturesPoster16 citations
765. Best of Both Worlds Policy OptimizationOral16 citations
766. Bit Allocation using OptimizationPoster16 citations
767. Deep Anomaly Detection under Labeling Budget ConstraintsPoster16 citations
768. Defects of Convolutional Decoder Networks in Frequency RepresentationPoster16 citations
769. Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram IterationPoster16 citations
770. Emergence of Sparse Representations from NoisePoster16 citations
771. Estimating Possible Causal Effects with Latent Variables via AdjustmentPoster16 citations
772. Exponential Smoothing for Off-Policy LearningOral16 citations
773. Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint ReductionPoster16 citations
774. Homomorphism AutoEncoder --- Learning Group Structured Representations from Observed TransitionsPoster16 citations
775. Improving Adversarial Robustness Through the Contrastive-Guided Diffusion ProcessPoster16 citations
776. Internally Rewarded Reinforcement LearningPoster16 citations
777. Leveraging Label Non-Uniformity for Node Classification in Graph Neural NetworksPoster16 citations
778. Leveraging Proxy of Training Data for Test-Time AdaptationPoster16 citations
779. Model-based Offline Reinforcement Learning with Count-based ConservatismPoster16 citations
780. MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient FlowsPoster16 citations
781. Orthogonality-Enforced Latent Space in Autoencoders: An Approach to Learning Disentangled RepresentationsPoster16 citations
782. Predicting Ordinary Differential Equations with TransformersPoster16 citations
783. Quantized Distributed Training of Large Models with Convergence GuaranteesPoster16 citations
784. Randomized Gaussian Process Upper Confidence Bound with Tighter Bayesian Regret BoundsPoster16 citations
785. Revisiting Pseudo-Label for Single-Positive Multi-Label LearningPoster16 citations
786. Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic ApproachPoster16 citations
787. Submodular Order Functions and Assortment OptimizationPoster16 citations
788. Supported Trust Region Optimization for Offline Reinforcement LearningPoster16 citations
789. Thompson Sampling for High-Dimensional Sparse Linear Contextual BanditsPoster16 citations
790. Thompson Sampling with Less Exploration is Fast and OptimalPoster16 citations
791. Topological Singularity Detection at Multiple ScalesPoster16 citations
792. Towards Constituting Mathematical Structures for Learning to OptimizePoster16 citations
793. Unconstrained Online Learning with Unbounded LossesPoster16 citations
794. User-level Private Stochastic Convex Optimization with Optimal RatesPoster16 citations
795. Width and Depth Limits Commute in Residual NetworksPoster16 citations
796. Adaptive Compositional Continual Meta-LearningPoster15 citations
797. Adversarial robustness of amortized Bayesian inferencePoster15 citations
798. Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent KernelsPoster15 citations
799. Are Large Kernels Better Teachers than Transformers for ConvNets?Poster15 citations
800. Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial ObservabilityPoster15 citations
801. Bayesian Design Principles for Frequentist Sequential LearningOral15 citations
802. Benign Overfitting in Deep Neural Networks under Lazy TrainingPoster15 citations
803. Certified Robust Neural Networks: Generalization and Corruption ResistancePoster15 citations
804. Cluster Explanation via Polyhedral DescriptionsPoster15 citations
805. Data Efficient Neural Scaling Law via Model ReusingPoster15 citations
806. Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust DecisionsPoster15 citations
807. Efficient Sequence Transduction by Jointly Predicting Tokens and DurationsPoster15 citations
808. Efficient Training of Language Models using Few-Shot LearningPoster15 citations
809. Explainable Data-Driven Optimization: From Context to Decision and Back AgainPoster15 citations
810. Fully Dynamic Submodular Maximization over MatroidsPoster15 citations
811. Gaussian processes at the Helm(holtz): A more fluid model for ocean currentsPoster15 citations
812. Graph Neural Tangent Kernel: Convergence on Large GraphsPoster15 citations
813. Improved Active Multi-Task Representation Learning via LassoPoster15 citations
814. Integrating Prior Knowledge in Contrastive Learning with KernelPoster15 citations
815. Low Complexity Homeomorphic Projection to Ensure Neural-Network Solution Feasibility for Optimization over (Non-)Convex SetPoster15 citations
816. MG-GNN: Multigrid Graph Neural Networks for Learning Multilevel Domain Decomposition MethodsPoster15 citations
817. Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear ProgrammingPoster15 citations
818. Motion Question Answering via Modular Motion ProgramsPoster15 citations
819. Near-Optimal $\Phi$-Regret Learning in Extensive-Form GamesPoster15 citations
820. Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally Coupled Oscillatory Recurrent Neural NetworksPoster15 citations
821. On Sampling with Approximate Transport MapsPoster15 citations
822. Provably Invariant Learning without Domain InformationPoster15 citations
823. QAS-Bench: Rethinking Quantum Architecture Search and A BenchmarkPoster15 citations
824. Random Grid Neural Processes for Parametric Partial Differential EquationsPoster15 citations
825. Reinforcement Learning Can Be More Efficient with Multiple RewardsPoster15 citations
826. STEP: Learning N:M Structured Sparsity Masks from Scratch with PreconditionPoster15 citations
827. Scaling Spherical CNNsPoster15 citations
828. Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time SeriesPoster15 citations
829. Stochastic Marginal Likelihood Gradients using Neural Tangent KernelsPoster15 citations
830. TabLeak: Tabular Data Leakage in Federated LearningPoster15 citations
831. Towards Bridging the Gaps between the Right to Explanation and the Right to be ForgottenPoster15 citations
832. Understanding Self-Distillation in the Presence of Label NoisePoster15 citations
833. Universal Morphology Control via Contextual ModulationPoster15 citations
834. Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection CapabilityPoster15 citations
835. Variational Autoencoding Neural OperatorsPoster15 citations
836. A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven PurificationPoster14 citations
837. A new near-linear time algorithm for k-nearest neighbor search using a compressed cover treePoster14 citations
838. Adaptive Computation with Elastic Input SequencePoster14 citations
839. Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural RepresentationsPoster14 citations
840. Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-CriticPoster14 citations
841. Causal Strategic Classification: A Tale of Two ShiftsPoster14 citations
842. Comparison of meta-learners for estimating multi-valued treatment heterogeneous effectsPoster14 citations
843. Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional EmbeddingsPoster14 citations
844. Concept-based Explanations for Out-of-Distribution DetectorsPoster14 citations
845. Curiosity in Hindsight: Intrinsic Exploration in Stochastic EnvironmentsPoster14 citations
846. Delving into Noisy Label Detection with Clean DataOral14 citations
847. End-to-End Learning for Stochastic Optimization: A Bayesian PerspectivePoster14 citations
848. Faster Gradient-Free Algorithms for Nonsmooth Nonconvex Stochastic OptimizationPoster14 citations
849. Flash: Concept Drift Adaptation in Federated LearningPoster14 citations
850. Functional Neural Networks: Shift invariant models for functional data with applications to EEG classificationPoster14 citations
851. Hardness of Independent Learning and Sparse Equilibrium Computation in Markov GamesPoster14 citations
852. Hierarchical Imitation Learning with Vector Quantized ModelsPoster14 citations
853. Identifiability and Generalizability in Constrained Inverse Reinforcement LearningPoster14 citations
854. Identifying Useful Learnwares for Heterogeneous Label SpacesPoster14 citations
855. Improved Learning-Augmented Algorithms for the Multi-Option Ski Rental Problem via Best-Possible Competitive AnalysisPoster14 citations
856. Long Horizon Temperature ScalingPoster14 citations
857. Modeling Dynamic Environments with Scene Graph MemoryPoster14 citations
858. Multi-task Hierarchical Adversarial Inverse Reinforcement LearningPoster14 citations
859. Offline Meta Reinforcement Learning with In-Distribution Online AdaptationPoster14 citations
860. Offline Reinforcement Learning with Closed-Form Policy Improvement OperatorsPoster14 citations
861. On User-Level Private Convex OptimizationPoster14 citations
862. Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your computePoster14 citations
863. Predictable MDP Abstraction for Unsupervised Model-Based RLPoster14 citations
864. Probabilistic Categorical Adversarial Attack and Adversarial TrainingPoster14 citations
865. Recasting Self-Attention with Holographic Reduced RepresentationsPoster14 citations
866. Revisiting Structured Variational AutoencodersPoster14 citations
867. Sample Complexity of Probability Divergences under Group SymmetryPoster14 citations
868. Self-Interpretable Time Series Prediction with Counterfactual ExplanationsOral14 citations
869. Sharper Bounds for $\ell_p$ Sensitivity SamplingOral14 citations
870. Smart Initial Basis Selection for Linear ProgramsPoster14 citations
871. The Test of Tests: A Framework for Differentially Private Hypothesis TestingPoster14 citations
872. The Virtues of Laziness in Model-based RL: A Unified Objective and AlgorithmsPoster14 citations
873. Towards Quantum Machine Learning for Constrained Combinatorial Optimization: a Quantum QAP SolverPoster14 citations
874. Towards Understanding and Reducing Graph Structural Noise for GNNsPoster14 citations
875. Understanding Backdoor Attacks through the Adaptability HypothesisPoster14 citations
876. Understanding the Distillation Process from Deep Generative Models to Tractable Probabilistic CircuitsPoster14 citations
877. Unifying Nesterov's Accelerated Gradient Methods for Convex and Strongly Convex Objective FunctionsOral14 citations
878. Variational Open-Domain Question AnsweringPoster14 citations
879. Vector-Valued Control VariatesPoster14 citations
880. A Kernel Stein Test of Goodness of Fit for Sequential ModelsPoster13 citations
881. A Large-Scale Study of Probabilistic Calibration in Neural Network RegressionPoster13 citations
882. ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical ImagingPoster13 citations
883. Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent KernelsOral13 citations
884. Building Neural Networks on Matrix Manifolds: A Gyrovector Space ApproachPoster13 citations
885. Causal Structure Learning for Latent Intervened Non-stationary DataPoster13 citations
886. Data Representations' Study of Latent Image ManifoldsPoster13 citations
887. Demystifying Disagreement-on-the-Line in High DimensionsPoster13 citations
888. Differentiable Multi-Target Causal Bayesian Experimental DesignPoster13 citations
889. Differentially Private Sharpness-Aware TrainingPoster13 citations
890. Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, RepeatPoster13 citations
891. Doubly Optimal No-Regret Learning in Monotone GamesPoster13 citations
892. Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over FunctionsPoster13 citations
893. Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic NeuronsPoster13 citations
894. E$(n)$ Equivariant Message Passing Simplicial NetworksPoster13 citations
895. Explore and Exploit the Diverse Knowledge in Model Zoo for Domain GeneralizationPoster13 citations
896. Fair yet Asymptotically Equal Collaborative LearningPoster13 citations
897. Feature Programming for Multivariate Time Series PredictionPoster13 citations
898. From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent ConfoundersPoster13 citations
899. Function-Space Regularization in Neural Networks: A Probabilistic PerspectivePoster13 citations
900. Generative Causal Representation Learning for Out-of-Distribution Motion ForecastingPoster13 citations
901. Geometric Autoencoders - What You See is What You DecodePoster13 citations
902. Git-Theta: A Git Extension for Collaborative Development of Machine Learning ModelsPoster13 citations
903. Hybrid Energy Based Model in the Feature Space for Out-of-Distribution DetectionPoster13 citations
904. Learning Compiler Pass Orders using Coreset and Normalized Value PredictionPoster13 citations
905. Learning Dynamic Query Combinations for Transformer-based Object Detection and SegmentationPoster13 citations
906. Learning Lightweight Object Detectors via Multi-Teacher Progressive DistillationPoster13 citations
907. MODeL: Memory Optimizations for Deep LearningPoster13 citations
908. Margin-based Neural Network WatermarkingPoster13 citations
909. Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular LearningPoster13 citations
910. Mixing Predictions for Online Metric AlgorithmsPoster13 citations
911. Model-Aware Contrastive Learning: Towards Escaping the DilemmasPoster13 citations
912. MyoDex: A Generalizable Prior for Dexterous ManipulationPoster13 citations
913. Nonparametric Generative Modeling with Conditional Sliced-Wasserstein FlowsPoster13 citations
914. On the Convergence of SARSA with Linear Function ApproximationPoster13 citations
915. Provably Learning Diverse Features in Multi-View Data with Midpoint MixupPoster13 citations
916. Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty EquivalentsPoster13 citations
917. Rethinking Weak Supervision in Helping Contrastive LearningPoster13 citations
918. Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural NetworksPoster13 citations
919. SemSup-XC: Semantic Supervision for Zero and Few-shot Extreme ClassificationPoster13 citations
920. Semi-Offline Reinforcement Learning for Optimized Text GenerationPoster13 citations
921. Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic EnvironmentsPoster13 citations
922. Subsample Ridge Ensembles: Equivalences and Generalized Cross-ValidationOral13 citations
923. The Role of Entropy and Reconstruction in Multi-View Self-Supervised LearningPoster13 citations
924. The Saddle-Point Method in Differential PrivacyPoster13 citations
925. The Value of Out-of-Distribution DataPoster13 citations
926. Towards Unbiased Training in Federated Open-world Semi-supervised LearningPoster13 citations
927. Uncertainty Estimation for Molecules: Desiderata and MethodsPoster13 citations
928. Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit BiasPoster13 citations
929. When Sparsity Meets Contrastive Models: Less Graph Data Can Bring Better Class-Balanced RepresentationsPoster13 citations
930. A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard ConstraintsPoster12 citations
931. A Statistical Perspective on Retrieval-Based ModelsPoster12 citations
932. Adaptive Coordination in Social Embodied RearrangementPoster12 citations
933. Additive Causal Bandits with Unknown GraphPoster12 citations
934. Alternately Optimized Graph Neural NetworksPoster12 citations
935. Automatic Data Augmentation via Invariance-Constrained LearningPoster12 citations
936. Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular BanditsPoster12 citations
937. Beyond the Edge of Stability via Two-step Gradient UpdatesPoster12 citations
938. Bilevel Optimization with Coupled Decision-Dependent DistributionsPoster12 citations
939. Combinatorial Neural BanditsPoster12 citations
940. Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative DifferentiationPoster12 citations
941. Compressed Decentralized Proximal Stochastic Gradient Method for Nonconvex Composite Problems with Heterogeneous DataPoster12 citations
942. Constrained Causal Bayesian OptimizationPoster12 citations
943. Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational AutoencodersPoster12 citations
944. Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function ApproximationPoster12 citations
945. Correcting discount-factor mismatch in on-policy policy gradient methodsPoster12 citations
946. Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?Oral12 citations
947. DiscoBAX - Discovery of optimal intervention sets in genomic experiment designPoster12 citations
948. DualHSIC: HSIC-Bottleneck and Alignment for Continual LearningPoster12 citations
949. Estimating Heterogeneous Treatment Effects: Mutual Information Bounds and Learning AlgorithmsPoster12 citations
950. Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov ChainsPoster12 citations
951. Fast Combinatorial Algorithms for Min Max Correlation ClusteringPoster12 citations
952. Fast Rates in Time-Varying Strongly Monotone GamesPoster12 citations
953. FedCR: Personalized Federated Learning Based on Across-Client Common Representation with Conditional Mutual Information RegularizationPoster12 citations
954. Federated Online and Bandit Convex OptimizationPoster12 citations
955. Gibbsian Polar Slice SamplingPoster12 citations
956. Improving l1-Certified Robustness via Randomized Smoothing by Leveraging Box ConstraintsPoster12 citations
957. Intrinsic Sliced Wasserstein Distances for Comparing Collections of Probability Distributions on Manifolds and GraphsPoster12 citations
958. Latent Traversals in Generative Models as Potential FlowsPoster12 citations
959. Learning Antidote Data to Individual UnfairnessPoster12 citations
960. Learning Belief Representations for Partially Observable Deep RLPoster12 citations
961. Learning Distributions over Quantum Measurement OutcomesPoster12 citations
962. Learning Instance-Specific Augmentations by Capturing Local InvariancesPoster12 citations
963. Linear optimal partial transport embeddingPoster12 citations
964. MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of BehaviorPoster12 citations
965. Magneto: A Foundation TransformerPoster12 citations
966. Model-Free Robust Average-Reward Reinforcement LearningPoster12 citations
967. MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera PosesPoster12 citations
968. Near-Optimal Algorithms for Private Online Optimization in the Realizable RegimePoster12 citations
969. Neural Network Approximations of PDEs Beyond Linearity: A Representational PerspectivePoster12 citations
970. Neural Prediction Errors enable Analogical Visual Reasoning in Human Standard Intelligence TestsPoster12 citations
971. Nonlinear Causal Discovery with Latent ConfoundersPoster12 citations
972. OCD: Learning to Overfit with Conditional Diffusion ModelsOral12 citations
973. On Distribution Dependent Sub-Logarithmic Query Time of Learned IndexingPoster12 citations
974. One-vs-the-Rest Loss to Focus on Important Samples in Adversarial TrainingPoster12 citations
975. Optimizing Mode Connectivity for Class Incremental LearningPoster12 citations
976. PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood AggregationPoster12 citations
977. PixelAsParam: A Gradient View on Diffusion Sampling with GuidancePoster12 citations
978. Properties of the Mallows Model Depending on the Number of Alternatives: A Warning for an ExperimentalistPoster12 citations
979. Provable Data Subset Selection For Efficient Neural Networks TrainingPoster12 citations
980. RLEG: Vision-Language Representation Learning with Diffusion-based Embedding GenerationPoster12 citations
981. Regions of Reliability in the Evaluation of Multivariate Probabilistic ForecastsPoster12 citations
982. Relevant Walk Search for Explaining Graph Neural NetworksPoster12 citations
983. Sequential Monte Carlo Learning for Time Series Structure DiscoveryPoster12 citations
984. Simplified Temporal Consistency Reinforcement LearningPoster12 citations
985. SlotGAT: Slot-based Message Passing for Heterogeneous GraphsPoster12 citations
986. Smooth Non-stationary BanditsPoster12 citations
987. Symmetry-Aware Robot Design with Structured SubgroupsPoster12 citations
988. Taxonomy-Structured Domain AdaptationPoster12 citations
989. Theoretical Behavior of XAI Methods in the Presence of Suppressor VariablesPoster12 citations
990. Total Variation Graph Neural NetworksPoster12 citations
991. Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial AttacksPoster12 citations
992. Unlocking Slot Attention by Changing Optimal Transport CostsPoster12 citations
993. When does Privileged information Explain Away Label Noise?Poster12 citations
994. Which Tricks are Important for Learning to Rank?Poster12 citations
995. A Mathematical Model for Curriculum Learning for ParitiesPoster11 citations
996. Adversarial Parameter Attack on Deep Neural NetworksPoster11 citations
997. Arithmetic Sampling: Parallel Diverse Decoding for Large Language ModelsOral11 citations
998. Boosting Offline Reinforcement Learning with Action Preference QueryPoster11 citations
999. Bootstrap in High Dimension with Low ComputationPoster11 citations
1000. COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision ModelsPoster11 citations

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