ICLR 2023 Accepted Papers

The full list of 1,575 papers accepted at ICLR 2023 (International Conference on Learning Representations). 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. ReAct: Synergizing Reasoning and Acting in Language ModelsTop-5%2,772 citations
2. DreamFusion: Text-to-3D using 2D DiffusionTop-5%2,361 citations
3. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object DetectionPoster1,881 citations
4. An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual InversionTop-25%1,810 citations
5. A Time Series is Worth 64 Words: Long-term Forecasting with TransformersPoster1,749 citations
6. Prompt-to-Prompt Image Editing with Cross-Attention ControlTop-25%1,736 citations
7. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsPoster1,586 citations
8. Least-to-Most Prompting Enables Complex Reasoning in Large Language ModelsPoster1,438 citations
9. Make-A-Video: Text-to-Video Generation without Text-Video DataPoster1,412 citations
10. TimesNet: Temporal 2D-Variation Modeling for General Time Series AnalysisPoster1,337 citations
11. Flow Matching for Generative ModelingTop-25%1,222 citations
12. CodeGen: An Open Large Language Model for Code with Multi-Turn Program SynthesisTop-25%1,177 citations
13. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding SharingPoster1,147 citations
14. Large Language Models are Human-Level Prompt EngineersPoster1,085 citations
15. Automatic Chain of Thought Prompting in Large Language ModelsPoster1,016 citations
16. Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series ForecastingTop-5%923 citations
17. Human Motion Diffusion ModelTop-25%921 citations
18. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified FlowTop-25%878 citations
19. Conditional Positional Encodings for Vision TransformersPoster802 citations
20. Diffusion Posterior Sampling for General Noisy Inverse ProblemsTop-25%784 citations
21. Quantifying Memorization Across Neural Language ModelsTop-25%776 citations
22. PaLI: A Jointly-Scaled Multilingual Language-Image ModelTop-5%736 citations
23. GLM-130B: An Open Bilingual Pre-trained ModelPoster715 citations
24. Vision Transformer Adapter for Dense PredictionsTop-25%699 citations
25. InCoder: A Generative Model for Code Infilling and SynthesisTop-25%688 citations
26. DiffDock: Diffusion Steps, Twists, and Turns for Molecular DockingPoster595 citations
27. CogVideo: Large-scale Pretraining for Text-to-Video Generation via TransformersPoster589 citations
28. Editing models with task arithmeticPoster588 citations
29. Simplified State Space Layers for Sequence ModelingTop-5%588 citations
30. Adaptive Budget Allocation for Parameter-Efficient Fine-TuningPoster581 citations
31. Socratic Models: Composing Zero-Shot Multimodal Reasoning with LanguageTop-25%559 citations
32. Mass-Editing Memory in a TransformerTop-25%533 citations
33. Hungry Hungry Hippos: Towards Language Modeling with State Space ModelsTop-25%521 citations
34. What learning algorithm is in-context learning? Investigations with linear modelsTop-5%517 citations
35. DiffEdit: Diffusion-based semantic image editing with mask guidanceTop-25%508 citations
36. Token Merging: Your ViT But FasterTop-5%505 citations
37. Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep LearningTop-5%496 citations
38. UL2: Unifying Language Learning ParadigmsPoster488 citations
39. Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 SmallPoster472 citations
40. Zero-Shot Image Restoration Using Denoising Diffusion Null-Space ModelTop-25%457 citations
41. Decomposed Prompting: A Modular Approach for Solving Complex TasksPoster452 citations
42. UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal TasksTop-25%446 citations
43. DiGress: Discrete Denoising diffusion for graph generationPoster445 citations
44. Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language GenerationTop-25%445 citations
45. Phenaki: Variable Length Video Generation from Open Domain Textual DescriptionsPoster440 citations
46. When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?Top-5%430 citations
47. Fast Sampling of Diffusion Models with Exponential IntegratorPoster425 citations
48. Complexity-Based Prompting for Multi-step ReasoningPoster416 citations
49. FreeMatch: Self-adaptive Thresholding for Semi-supervised LearningPoster413 citations
50. Is Conditional Generative Modeling all you need for Decision Making?Top-5%413 citations
51. Visual Classification via Description from Large Language ModelsTop-5%406 citations
52. AudioGen: Textually Guided Audio GenerationPoster400 citations
53. Progress measures for grokking via mechanistic interpretabilityTop-25%397 citations
54. Selection-Inference: Exploiting Large Language Models for Interpretable Logical ReasoningTop-5%384 citations
55. Diffusion Policies as an Expressive Policy Class for Offline Reinforcement LearningPoster377 citations
56. Uni-Mol: A Universal 3D Molecular Representation Learning FrameworkPoster377 citations
57. Building Normalizing Flows with Stochastic InterpolantsPoster369 citations
58. Last Layer Re-Training is Sufficient for Robustness to Spurious CorrelationsTop-25%363 citations
59. DiffuSeq: Sequence to Sequence Text Generation with Diffusion ModelsPoster355 citations
60. CodeT: Code Generation with Generated TestsPoster352 citations
61. Git Re-Basin: Merging Models modulo Permutation SymmetriesTop-5%351 citations
62. TabPFN: A Transformer That Solves Small Tabular Classification Problems in a SecondTop-25%344 citations
63. Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionsTop-5%335 citations
64. LightGCL: Simple Yet Effective Graph Contrastive Learning for RecommendationTop-25%333 citations
65. MICN: Multi-scale Local and Global Context Modeling for Long-term Series ForecastingTop-5%333 citations
66. IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?Top-25%331 citations
67. Language models are multilingual chain-of-thought reasonersPoster331 citations
68. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image SynthesisPoster326 citations
69. Discovering Latent Knowledge in Language Models Without SupervisionPoster321 citations
70. Spikformer: When Spiking Neural Network Meets TransformerPoster317 citations
71. Generate rather than Retrieve: Large Language Models are Strong Context GeneratorsPoster316 citations
72. Analog Bits: Generating Discrete Data using Diffusion Models with Self-ConditioningPoster305 citations
73. Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic TaskTop-5%304 citations
74. Towards Stable Test-time Adaptation in Dynamic Wild WorldTop-5%303 citations
75. VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-TrainingTop-25%295 citations
76. Diffusion-GAN: Training GANs with DiffusionPoster290 citations
77. Prompting GPT-3 To Be ReliablePoster287 citations
78. Pseudoinverse-Guided Diffusion Models for Inverse ProblemsPoster285 citations
79. Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-ThoughtPoster279 citations
80. BigVGAN: A Universal Neural Vocoder with Large-Scale TrainingPoster278 citations
81. Novel View Synthesis with Diffusion ModelsPoster277 citations
82. Reward Design with Language ModelsPoster277 citations
83. Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problemPoster275 citations
84. Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical ReasoningPoster273 citations
85. MapTR: Structured Modeling and Learning for Online Vectorized HD Map ConstructionTop-25%270 citations
86. Long Range Language Modeling via Gated State SpacesPoster267 citations
87. Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic GraphsTop-25%262 citations
88. Post-hoc Concept Bottleneck ModelsTop-25%255 citations
89. Diffusion Models Already Have A Semantic Latent SpaceTop-25%254 citations
90. Language Models are Realistic Tabular Data GeneratorsPoster253 citations
91. Protein Representation Learning by Geometric Structure PretrainingPoster249 citations
92. Ask Me Anything: A simple strategy for prompting language modelsTop-25%248 citations
93. More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using SparsityPoster246 citations
94. A critical look at the evaluation of GNNs under heterophily: Are we really making progress?Poster244 citations
95. SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised LearningPoster241 citations
96. The KFIoU Loss for Rotated Object DetectionPoster239 citations
97. Promptagator: Few-shot Dense Retrieval From 8 ExamplesPoster230 citations
98. AIM: Adapting Image Models for Efficient Video Action RecognitionPoster229 citations
99. Surgical Fine-Tuning Improves Adaptation to Distribution ShiftsPoster229 citations
100. Open-Vocabulary Object Detection upon Frozen Vision and Language ModelsPoster228 citations
101. Dual Diffusion Implicit Bridges for Image-to-Image TranslationPoster227 citations
102. A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental LearningTop-25%221 citations
103. The Role of ImageNet Classes in Fréchet Inception DistanceTop-25%216 citations
104. Imitating Human Behaviour with Diffusion ModelsPoster214 citations
105. Selective Annotation Makes Language Models Better Few-Shot LearnersPoster214 citations
106. Transformers Learn Shortcuts to AutomataTop-5%213 citations
107. 3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image SegmentationPoster210 citations
108. Label-free Concept Bottleneck ModelsPoster202 citations
109. Dataless Knowledge Fusion by Merging Weights of Language ModelsPoster201 citations
110. Re-Imagen: Retrieval-Augmented Text-to-Image GeneratorPoster198 citations
111. 3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity PredictionPoster197 citations
112. Transformers are Sample-Efficient World ModelsTop-5%197 citations
113. Binding Language Models in Symbolic LanguagesTop-25%195 citations
114. How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?Poster193 citations
115. Sign and Basis Invariant Networks for Spectral Graph Representation LearningTop-25%193 citations
116. Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object DetectionTop-5%192 citations
117. Extremely Simple Activation Shaping for Out-of-Distribution DetectionPoster190 citations
118. Leveraging Large Language Models for Multiple Choice Question AnsweringPoster189 citations
119. SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic SegmentationPoster189 citations
120. Visual Recognition with Deep Nearest CentroidsTop-25%183 citations
121. Factorized Fourier Neural OperatorsPoster177 citations
122. Formal Mathematics Statement Curriculum LearningTop-25%177 citations
123. PLOT: Prompt Learning with Optimal Transport for Vision-Language ModelsTop-25%177 citations
124. Planning with Large Language Models for Code GenerationPoster177 citations
125. MeshDiffusion: Score-based Generative 3D Mesh ModelingTop-25%175 citations
126. NAGphormer: A Tokenized Graph Transformer for Node Classification in Large GraphsPoster175 citations
127. Diffusion-based Image Translation using disentangled style and content representationPoster173 citations
128. Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal ProofsTop-5%172 citations
129. Selective Frequency Network for Image RestorationPoster169 citations
130. Mole-BERT: Rethinking Pre-training Graph Neural Networks for MoleculesPoster167 citations
131. Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental LearningTop-25%166 citations
132. Transformer-Patcher: One Mistake Worth One NeuronPoster164 citations
133. Personalized Federated Learning with Feature Alignment and Classifier CollaborationTop-5%163 citations
134. Progressive Prompts: Continual Learning for Language ModelsPoster161 citations
135. Learning on Large-scale Text-attributed Graphs via Variational InferenceTop-5%158 citations
136. Contrastive Audio-Visual Masked AutoencoderTop-25%156 citations
137. Do We Really Need Complicated Model Architectures For Temporal Networks?Top-5%156 citations
138. DocPrompting: Generating Code by Retrieving the DocsTop-25%155 citations
139. Neural Networks and the Chomsky HierarchyTop-25%155 citations
140. Compositional Semantic Parsing with Large Language ModelsPoster150 citations
141. Continual Pre-training of Language ModelsPoster149 citations
142. Embedding Fourier for Ultra-High-Definition Low-Light Image EnhancementTop-5%147 citations
143. GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face SynthesisPoster147 citations
144. In-context Reinforcement Learning with Algorithm DistillationTop-5%145 citations
145. Pre-training via Denoising for Molecular Property PredictionTop-25%145 citations
146. Bridging the Gap to Real-World Object-Centric LearningPoster144 citations
147. SQA3D: Situated Question Answering in 3D ScenesPoster142 citations
148. Calibrating Sequence likelihood Improves Conditional Language GenerationPoster140 citations
149. kNN-Diffusion: Image Generation via Large-Scale RetrievalPoster139 citations
150. Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked ModelingTop-25%138 citations
151. Rethinking the Expressive Power of GNNs via Graph BiconnectivityTop-5%138 citations
152. Multi-lingual Evaluation of Code Generation ModelsTop-25%137 citations
153. Towards the Generalization of Contrastive Self-Supervised LearningPoster137 citations
154. Dataset Pruning: Reducing Training Data by Examining Generalization InfluencePoster135 citations
155. MaskViT: Masked Visual Pre-Training for Video PredictionPoster135 citations
156. Accurate Image Restoration with Attention Retractable TransformerTop-25%134 citations
157. TEMPERA: Test-Time Prompt Editing via Reinforcement LearningTop-25%134 citations
158. Graph Neural Networks for Link Prediction with Subgraph SketchingTop-5%133 citations
159. Liquid Structural State-Space ModelsPoster132 citations
160. Recitation-Augmented Language ModelsPoster131 citations
161. Where to Begin? On the Impact of Pre-Training and Initialization in Federated LearningTop-25%131 citations
162. PiFold: Toward effective and efficient protein inverse foldingTop-25%130 citations
163. PEER: A Collaborative Language ModelTop-25%129 citations
164. gDDIM: Generalized denoising diffusion implicit modelsTop-25%129 citations
165. Multitask Prompt Tuning Enables Parameter-Efficient Transfer LearningPoster128 citations
166. Scaleformer: Iterative Multi-scale Refining Transformers for Time Series ForecastingPoster125 citations
167. Revisiting the Assumption of Latent Separability for Backdoor DefensesPoster124 citations
168. DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained DiffusionTop-25%123 citations
169. EVA3D: Compositional 3D Human Generation from 2D Image CollectionsTop-25%123 citations
170. Generating Sequences by Learning to Self-CorrectPoster122 citations
171. ROSCOE: A Suite of Metrics for Scoring Step-by-Step ReasoningTop-25%122 citations
172. Non-parametric Outlier SynthesisPoster121 citations
173. Sparse Upcycling: Training Mixture-of-Experts from Dense CheckpointsPoster119 citations
174. One Transformer Can Understand Both 2D & 3D Molecular DataPoster117 citations
175. How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis ProjectionsPoster116 citations
176. On the duality between contrastive and non-contrastive self-supervised learningTop-5%116 citations
177. Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio BarrierTop-5%116 citations
178. What Makes Convolutional Models Great on Long Sequence Modeling?Poster116 citations
179. DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only TrainingPoster115 citations
180. Linearly Mapping from Image to Text SpacePoster115 citations
181. Measuring Forgetting of Memorized Training ExamplesPoster112 citations
182. TTN: A Domain-Shift Aware Batch Normalization in Test-Time AdaptationPoster111 citations
183. ManiSkill2: A Unified Benchmark for Generalizable Manipulation SkillsPoster110 citations
184. Learning Object-Language Alignments for Open-Vocabulary Object DetectionPoster109 citations
185. Offline RL for Natural Language Generation with Implicit Language Q LearningPoster109 citations
186. Specformer: Spectral Graph Neural Networks Meet TransformersPoster109 citations
187. Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy OptimizationTop-25%108 citations
188. Omnigrok: Grokking Beyond Algorithmic DataTop-25%108 citations
189. Offline Reinforcement Learning via High-Fidelity Generative Behavior ModelingPoster107 citations
190. S-NeRF: Neural Radiance Fields for Street ViewsPoster107 citations
191. SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction ConsistencyPoster107 citations
192. Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?Poster106 citations
193. Clifford Neural Layers for PDE ModelingPoster106 citations
194. Generative Modelling with Inverse Heat DissipationPoster106 citations
195. Multimodal Federated Learning via Contrastive Representation EnsemblePoster106 citations
196. Out-of-Distribution Detection and Selective Generation for Conditional Language ModelsTop-25%106 citations
197. Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep LearningPoster102 citations
198. UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge GraphPoster102 citations
199. CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision NetworksTop-25%101 citations
200. Relative representations enable zero-shot latent space communicationTop-5%101 citations
201. Reversible Column NetworksPoster101 citations
202. Voxurf: Voxel-based Efficient and Accurate Neural Surface ReconstructionTop-25%101 citations
203. DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge BasesPoster100 citations
204. SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric ModelsPoster100 citations
205. What Do Self-Supervised Vision Transformers Learn?Poster98 citations
206. Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance FieldsPoster97 citations
207. Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of StabilityPoster96 citations
208. Mega: Moving Average Equipped Gated AttentionPoster95 citations
209. Hybrid RL: Using both offline and online data can make RL efficientPoster94 citations
210. Corrupted Image Modeling for Self-Supervised Visual Pre-TrainingTop-25%93 citations
211. Learning to Compose Soft Prompts for Compositional Zero-Shot LearningPoster93 citations
212. Offline RL with No OOD Actions: In-Sample Learning via Implicit Value RegularizationTop-5%93 citations
213. GFlowNets and variational inferencePoster92 citations
214. Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance MatchingPoster92 citations
215. The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in TransformersPoster92 citations
216. On the Importance and Applicability of Pre-Training for Federated LearningPoster91 citations
217. Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingPoster91 citations
218. Preference Transformer: Modeling Human Preferences using Transformers for RLPoster91 citations
219. Discrete Contrastive Diffusion for Cross-Modal Music and Image GenerationPoster90 citations
220. Energy-based Out-of-Distribution Detection for Graph Neural NetworksPoster90 citations
221. FoSR: First-order spectral rewiring for addressing oversquashing in GNNsPoster89 citations
222. MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPCTop-25%89 citations
223. The Role of Coverage in Online Reinforcement LearningTop-5%89 citations
224. Human alignment of neural network representationsPoster88 citations
225. MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDYPoster88 citations
226. Masked Frequency Modeling for Self-Supervised Visual Pre-TrainingPoster88 citations
227. REPAIR: REnormalizing Permuted Activations for Interpolation RepairPoster87 citations
228. Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated LearningPoster87 citations
229. Transformer-based World Models Are Happy With 100k InteractionsPoster87 citations
230. Code Translation with Compiler RepresentationsTop-25%86 citations
231. Conditional Antibody Design as 3D Equivariant Graph TranslationTop-5%86 citations
232. Distilling Model Failures as Directions in Latent SpaceTop-25%86 citations
233. Diffusion Adversarial Representation Learning for Self-supervised Vessel SegmentationPoster85 citations
234. BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object DetectionPoster84 citations
235. Denoising Diffusion SamplersPoster84 citations
236. LPT: Long-tailed Prompt Tuning for Image ClassificationPoster84 citations
237. Mind's Eye: Grounded Language Model Reasoning through SimulationPoster84 citations
238. NORM: Knowledge Distillation via N-to-One Representation MatchingPoster84 citations
239. Sparse Mixture-of-Experts are Domain Generalizable LearnersTop-5%84 citations
240. A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample ComplexityPoster83 citations
241. Broken Neural Scaling LawsPoster83 citations
242. From Play to Policy: Conditional Behavior Generation from Uncurated Robot DataTop-5%83 citations
243. MEDFAIR: Benchmarking Fairness for Medical ImagingTop-25%83 citations
244. Understanding Zero-shot Adversarial Robustness for Large-Scale ModelsPoster83 citations
245. Continuous PDE Dynamics Forecasting with Implicit Neural RepresentationsTop-25%82 citations
246. Explicit Box Detection Unifies End-to-End Multi-Person Pose EstimationPoster82 citations
247. Flow Annealed Importance Sampling BootstrapTop-25%82 citations
248. PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System IdentificationTop-25%82 citations
249. Agree to Disagree: Diversity through Disagreement for Better TransferabilityTop-5%81 citations
250. Blurring Diffusion ModelsPoster81 citations
251. Image as Set of PointsTop-5%81 citations
252. Extreme Q-Learning: MaxEnt RL without EntropyTop-5%80 citations
253. Score-based Continuous-time Discrete Diffusion ModelsPoster80 citations
254. ZiCo: Zero-shot NAS via inverse Coefficient of Variation on GradientsTop-25%80 citations
255. Empowering Graph Representation Learning with Test-Time Graph TransformationPoster79 citations
256. Language Models Can Teach Themselves to Program BetterPoster79 citations
257. Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and EfficiencyTop-25%79 citations
258. Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: GraphcorePoster79 citations
259. STaSy: Score-based Tabular data SynthesisTop-25%79 citations
260. H2RBox: Horizontal Box Annotation is All You Need for Oriented Object DetectionPoster78 citations
261. Leveraging Future Relationship Reasoning for Vehicle Trajectory PredictionPoster78 citations
262. MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision ModelsPoster78 citations
263. Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPsPoster77 citations
264. Contrastive Learning for Unsupervised Domain Adaptation of Time SeriesPoster76 citations
265. EVC: Towards Real-Time Neural Image Compression with Mask DecayPoster76 citations
266. GOGGLE: Generative Modelling for Tabular Data by Learning Relational StructurePoster76 citations
267. Learning Hierarchical Protein Representations via Complete 3D Graph NetworksPoster76 citations
268. Masked Vision and Language Modeling for Multi-modal Representation LearningPoster76 citations
269. BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and FusionPoster75 citations
270. DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATIONPoster75 citations
271. DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D ImagesPoster75 citations
272. Policy Expansion for Bridging Offline-to-Online Reinforcement LearningPoster75 citations
273. Anti-Symmetric DGN: a stable architecture for Deep Graph NetworksPoster74 citations
274. HiViT: A Simpler and More Efficient Design of Hierarchical Vision TransformerTop-25%74 citations
275. Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree searchTop-5%74 citations
276. Can CNNs Be More Robust Than Transformers?Poster73 citations
277. Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language ModelsPoster72 citations
278. FedExP: Speeding Up Federated Averaging via ExtrapolationTop-25%72 citations
279. Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might BePoster72 citations
280. DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion ModelsPoster71 citations
281. Equivariant Energy-Guided SDE for Inverse Molecular DesignPoster71 citations
282. Neural Networks Efficiently Learn Low-Dimensional Representations with SGDTop-25%71 citations
283. Parameter-Efficient Fine-Tuning Design SpacesPoster71 citations
284. A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum GamesPoster70 citations
285. Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution GeneralizationPoster70 citations
286. Global Explainability of GNNs via Logic Combination of Learned ConceptsPoster69 citations
287. LAVA: Data Valuation without Pre-Specified Learning AlgorithmsTop-25%69 citations
288. Advancing Radiograph Representation Learning with Masked Record ModelingPoster68 citations
289. Coverage-centric Coreset Selection for High Pruning RatesPoster68 citations
290. Gradient Gating for Deep Multi-Rate Learning on GraphsPoster68 citations
291. Optimizing Bi-Encoder for Named Entity Recognition via Contrastive LearningPoster68 citations
292. PINTO: Faithful Language Reasoning Using Prompt-Generated RationalesPoster68 citations
293. Sparse Random Networks for Communication-Efficient Federated LearningPoster68 citations
294. FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization AccuracyPoster67 citations
295. Learning to Grow Pretrained Models for Efficient Transformer TrainingTop-25%67 citations
296. Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield EnergyPoster67 citations
297. StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at RandomPoster67 citations
298. Test-Time Adaptation via Self-Training with Nearest Neighbor InformationPoster67 citations
299. Bidirectional Language Models Are Also Few-shot LearnersPoster66 citations
300. Equivariant Hypergraph Diffusion Neural OperatorsPoster66 citations
301. NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex ScenesPoster66 citations
302. Better Generative Replay for Continual Federated LearningPoster65 citations
303. Certified Training: Small Boxes are All You NeedTop-25%65 citations
304. Out-of-distribution Representation Learning for Time Series ClassificationPoster65 citations
305. Re-parameterizing Your Optimizers rather than ArchitecturesPoster65 citations
306. Statistical Efficiency of Score Matching: The View from IsoperimetryTop-5%65 citations
307. VA-DepthNet: A Variational Approach to Single Image Depth PredictionTop-25%65 citations
308. How Sharpness-Aware Minimization Minimizes Sharpness?Poster64 citations
309. On the Soft-Subnetwork for Few-Shot Class Incremental LearningPoster64 citations
310. Spotlight: Mobile UI Understanding using Vision-Language Models with a FocusPoster64 citations
311. Batch Multivalid Conformal PredictionPoster63 citations
312. Understanding the Generalization of Adam in Learning Neural Networks with Proper RegularizationPoster63 citations
313. Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot LearningTop-25%63 citations
314. An efficient encoder-decoder architecture with top-down attention for speech separationPoster62 citations
315. Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence ModelPoster62 citations
316. NANSY++: Unified Voice Synthesis with Neural Analysis and SynthesisPoster62 citations
317. SLTUNET: A Simple Unified Model for Sign Language TranslationPoster62 citations
318. Spectral Augmentation for Self-Supervised Learning on GraphsTop-25%62 citations
319. Data augmentation alone can improve adversarial trainingPoster61 citations
320. Free Lunch for Domain Adversarial Training: Environment Label SmoothingPoster61 citations
321. Hebbian Deep Learning Without FeedbackTop-25%61 citations
322. Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional DataTop-25%61 citations
323. Neural Optimal TransportTop-25%61 citations
324. Offline Q-learning on Diverse Multi-Task Data Both Scales And GeneralizesTop-5%61 citations
325. 3D generation on ImageNetTop-5%60 citations
326. A Unified Algebraic Perspective on Lipschitz Neural NetworksTop-25%60 citations
327. Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge DistillationPoster60 citations
328. CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural RepresentationsTop-25%60 citations
329. GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural NetworksPoster60 citations
330. General Neural Gauge FieldsPoster60 citations
331. Graph Domain Adaptation via Theory-Grounded Spectral RegularizationPoster60 citations
332. Multi-skill Mobile Manipulation for Object RearrangementTop-25%60 citations
333. Neural Compositional Rule Learning for Knowledge Graph ReasoningPoster60 citations
334. Scaling Forward Gradient With Local LossesPoster60 citations
335. TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene UnderstandingPoster60 citations
336. The hidden uniform cluster prior in self-supervised learningPoster60 citations
337. Understanding DDPM Latent Codes Through Optimal TransportPoster60 citations
338. Causal Confusion and Reward Misidentification in Preference-Based Reward LearningPoster59 citations
339. Learning Fair Graph Representations via Automated Data AugmentationsTop-25%59 citations
340. Learning to Induce Causal StructurePoster59 citations
341. Robust Scheduling with GFlowNetsPoster59 citations
342. Towards Interpretable Deep Reinforcement Learning with Human-Friendly PrototypesTop-25%59 citations
343. Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNsPoster58 citations
344. Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-timePoster58 citations
345. Harnessing Out-Of-Distribution Examples via Augmenting Content and StylePoster58 citations
346. Learning Fast and Slow for Online Time Series ForecastingPoster58 citations
347. On Representing Linear Programs by Graph Neural NetworksTop-25%58 citations
348. Continual evaluation for lifelong learning: Identifying the stability gapTop-25%57 citations
349. Effectively Modeling Time Series with Simple Discrete State SpacesPoster57 citations
350. FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated LearningPoster57 citations
351. Jointly Learning Visual and Auditory Speech Representations from Raw DataPoster57 citations
352. Test-Time Robust Personalization for Federated LearningPoster57 citations
353. When Source-Free Domain Adaptation Meets Learning with Noisy LabelsTop-25%57 citations
354. Deep Learning on Implicit Neural Representations of ShapesPoster56 citations
355. Is Attention All That NeRF Needs?Poster56 citations
356. Molecule Generation For Target Protein Binding with Structural MotifsPoster56 citations
357. UniMax: Fairer and More Effective Language Sampling for Large-Scale Multilingual PretrainingPoster56 citations
358. Diagnosing and Rectifying Vision Models using LanguagePoster55 citations
359. Discovering Evolution Strategies via Meta-Black-Box OptimizationPoster55 citations
360. Improving Deep Regression with Ordinal EntropyPoster55 citations
361. MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP InitializationPoster55 citations
362. Masked Image Modeling with Denoising ContrastPoster55 citations
363. Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and PlanningTop-5%55 citations
364. Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent ApproachTop-5%55 citations
365. StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-trainingPoster55 citations
366. TILP: Differentiable Learning of Temporal Logical Rules on Knowledge GraphsPoster55 citations
367. A Self-Attention Ansatz for Ab-initio Quantum ChemistryPoster54 citations
368. CUDA: Curriculum of Data Augmentation for Long-tailed RecognitionTop-25%54 citations
369. Diffusion Models for Causal Discovery via Topological OrderingPoster54 citations
370. Edge Guided GANs with Contrastive Learning for Semantic Image SynthesisPoster54 citations
371. Efficient Model Updates for Approximate Unlearning of Graph-Structured DataPoster54 citations
372. Language Modelling with PixelsTop-5%54 citations
373. Linear Connectivity Reveals Generalization StrategiesPoster54 citations
374. Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov GamePoster54 citations
375. Out-of-distribution Detection with Implicit Outlier TransformationPoster54 citations
376. SMART: Self-supervised Multi-task pretrAining with contRol TransformersTop-25%54 citations
377. Temporal Domain Generalization with Drift-Aware Dynamic Neural NetworksTop-5%54 citations
378. Unsupervised Semantic Segmentation with Self-supervised Object-centric RepresentationsTop-25%54 citations
379. ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic ConsistencyPoster54 citations
380. A Call to Reflect on Evaluation Practices for Failure Detection in Image ClassificationTop-5%53 citations
381. A Non-Asymptotic Analysis of Oversmoothing in Graph Neural NetworksPoster53 citations
382. CUTS: Neural Causal Discovery from Irregular Time-Series DataPoster53 citations
383. Concept-level Debugging of Part-Prototype NetworksTop-25%53 citations
384. LMC: Fast Training of GNNs via Subgraph Sampling with Provable ConvergenceTop-25%53 citations
385. Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable TransformersTop-25%53 citations
386. $k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor InferencePoster52 citations
387. Bridging the Gap between ANNs and SNNs by Calibrating Offset SpikesPoster52 citations
388. DepthFL : Depthwise Federated Learning for Heterogeneous ClientsPoster52 citations
389. Exploring the Limits of Differentially Private Deep Learning with Group-wise ClippingPoster52 citations
390. SimPer: Simple Self-Supervised Learning of Periodic TargetsTop-5%52 citations
391. The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge DistillationTop-5%52 citations
392. Unsupervised Model Selection for Time Series Anomaly DetectionTop-25%52 citations
393. DENSE RGB SLAM WITH NEURAL IMPLICIT MAPSPoster51 citations
394. HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware AttentionPoster51 citations
395. Linear Convergence of Natural Policy Gradient Methods with Log-Linear PoliciesPoster51 citations
396. PAC Reinforcement Learning for Predictive State RepresentationsPoster51 citations
397. Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement LearningTop-25%51 citations
398. Reliability of CKA as a Similarity Measure in Deep LearningPoster51 citations
399. Retrieval-based Controllable Molecule GenerationTop-25%51 citations
400. The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge DistillationPoster51 citations
401. ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural NetworksTop-25%50 citations
402. Continuous-Discrete Convolution for Geometry-Sequence Modeling in ProteinsPoster50 citations
403. ContraNorm: A Contrastive Learning Perspective on Oversmoothing and BeyondPoster50 citations
404. Data-Free One-Shot Federated Learning Under Very High Statistical HeterogeneityPoster50 citations
405. Dichotomy of Control: Separating What You Can Control from What You CannotTop-5%50 citations
406. Does Zero-Shot Reinforcement Learning Exist?Top-25%50 citations
407. FluidLab: A Differentiable Environment for Benchmarking Complex Fluid ManipulationTop-25%50 citations
408. ImageNet-X: Understanding Model Mistakes with Factor of Variation AnnotationsTop-25%50 citations
409. Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic RecoursePoster50 citations
410. Trainability Preserving Neural PruningPoster50 citations
411. Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?Top-25%50 citations
412. Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the TopPoster50 citations
413. simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge TracingPoster50 citations
414. Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation LearningPoster49 citations
415. FedFA: Federated Feature AugmentationPoster49 citations
416. MoDem: Accelerating Visual Model-Based Reinforcement Learning with DemonstrationsPoster49 citations
417. POPGym: Benchmarking Partially Observable Reinforcement LearningPoster49 citations
418. TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased RecommendationsPoster49 citations
419. TranSpeech: Speech-to-Speech Translation With Bilateral PerturbationPoster49 citations
420. Behavior Proximal Policy OptimizationPoster48 citations
421. GNNDelete: A General Strategy for Unlearning in Graph Neural NetworksPoster48 citations
422. Identifiability Results for Multimodal Contrastive LearningPoster48 citations
423. Improving Object-centric Learning with Query OptimizationPoster48 citations
424. Neural Systematic BinderPoster48 citations
425. PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning AlgorithmPoster48 citations
426. Transfer Learning with Deep Tabular ModelsPoster48 citations
427. Classically Approximating Variational Quantum Machine Learning with Random Fourier FeaturesPoster47 citations
428. Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels OnlyTop-5%47 citations
429. Human-level Atari 200x fasterPoster47 citations
430. Optimal Conservative Offline RL with General Function Approximation via Augmented LagrangianTop-25%47 citations
431. Protein Sequence and Structure Co-Design with Equivariant TranslationPoster47 citations
432. Prototypical Calibration for Few-shot Learning of Language ModelsPoster47 citations
433. Spherical Sliced-WassersteinPoster47 citations
434. Transferable Unlearnable ExamplesPoster47 citations
435. UNICORN: A Unified Backdoor Trigger Inversion FrameworkTop-25%47 citations
436. Efficient Planning in a Compact Latent Action SpacePoster46 citations
437. Exploring and Exploiting Decision Boundary Dynamics for Adversarial RobustnessPoster46 citations
438. Federated Learning from Small DatasetsPoster46 citations
439. Generative Augmented Flow NetworksTop-25%46 citations
440. Relational Attention: Generalizing Transformers for Graph-Structured TasksTop-25%46 citations
441. Spiking Convolutional Neural Networks for Text ClassificationPoster46 citations
442. Temperature Schedules for self-supervised contrastive methods on long-tail dataPoster46 citations
443. Verifying the Union of Manifolds Hypothesis for Image DataPoster46 citations
444. Characterizing intrinsic compositionality in transformers with Tree ProjectionsPoster45 citations
445. Context-enriched molecule representations improve few-shot drug discoveryPoster45 citations
446. Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov GamesPoster45 citations
447. Multi-level Protein Structure Pre-training via Prompt LearningPoster45 citations
448. OTOv2: Automatic, Generic, User-FriendlyPoster45 citations
449. RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal UpdatesPoster45 citations
450. SIMPLE: Specialized Model-Sample Matching for Domain GeneralizationPoster45 citations
451. The In-Sample Softmax for Offline Reinforcement LearningTop-25%45 citations
452. Understanding Edge-of-Stability Training Dynamics with a Minimalist ExamplePoster45 citations
453. E3Bind: An End-to-End Equivariant Network for Protein-Ligand DockingPoster44 citations
454. Hyper-Decision Transformer for Efficient Online Policy AdaptationPoster44 citations
455. Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action RepresentationsPoster44 citations
456. Learning to Linearize Deep Neural Networks for Secure and Efficient Private InferencePoster44 citations
457. Modeling content creator incentives on algorithm-curated platformsTop-5%44 citations
458. On the Robustness of Safe Reinforcement Learning under Observational PerturbationsPoster44 citations
459. The Lie Derivative for Measuring Learned EquivarianceTop-5%44 citations
460. Causal Imitation Learning via Inverse Reinforcement LearningPoster43 citations
461. CktGNN: Circuit Graph Neural Network for Electronic Design AutomationPoster43 citations
462. De Novo Molecular Generation via Connection-aware Motif MiningPoster43 citations
463. Deep Generative Symbolic RegressionPoster43 citations
464. DensePure: Understanding Diffusion Models for Adversarial RobustnessPoster43 citations
465. Dirichlet-based Uncertainty Calibration for Active Domain AdaptationTop-25%43 citations
466. Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image ClassificationPoster43 citations
467. Knowledge Distillation based Degradation Estimation for Blind Super-ResolutionPoster43 citations
468. LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale RetrievalPoster43 citations
469. MultiViz: Towards Visualizing and Understanding Multimodal ModelsPoster43 citations
470. Recon: Reducing Conflicting Gradients From the Root For Multi-Task LearningPoster43 citations
471. Unicom: Universal and Compact Representation Learning for Image RetrievalPoster43 citations
472. Accelerated Single-Call Methods for Constrained Min-Max OptimizationPoster42 citations
473. Dilated convolution with learnable spacingsPoster42 citations
474. Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near OptimalityPoster42 citations
475. Graph Contrastive Learning for Skeleton-based Action RecognitionPoster42 citations
476. How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit RegularizationPoster42 citations
477. Masked Distillation with Receptive TokensPoster42 citations
478. Masked Unsupervised Self-training for Label-free Image ClassificationPoster42 citations
479. Pruning Deep Neural Networks from a Sparsity PerspectivePoster42 citations
480. Using Language to Extend to Unseen DomainsTop-25%42 citations
481. A framework for benchmarking Class-out-of-distribution detection and its application to ImageNetTop-25%41 citations
482. Effects of Graph Convolutions in Multi-layer NetworksTop-25%41 citations
483. MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement LearningPoster41 citations
484. MECTA: Memory-Economic Continual Test-Time Model AdaptationPoster41 citations
485. Meta Knowledge Condensation for Federated LearningPoster41 citations
486. Unbiased Supervised Contrastive LearningPoster41 citations
487. A Graph Neural Network Approach to Automated Model Building in Cryo-EM MapsPoster40 citations
488. Causal Representation Learning for Instantaneous and Temporal Effects in Interactive SystemsPoster40 citations
489. Competitive Physics Informed NetworksPoster40 citations
490. Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box PredictorsTop-25%40 citations
491. Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge NetworksPoster40 citations
492. ExpressivE: A Spatio-Functional Embedding For Knowledge Graph CompletionTop-25%40 citations
493. Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property PredictionPoster40 citations
494. Policy Pre-training for Autonomous Driving via Self-supervised Geometric ModelingPoster40 citations
495. Programmatically Grounded, Compositionally Generalizable Robotic ManipulationTop-25%40 citations
496. WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable SimulationsPoster40 citations
497. Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty AggregationPoster39 citations
498. BrainBERT: Self-supervised representation learning for intracranial recordingsPoster39 citations
499. Building a Subspace of Policies for Scalable Continual LearningTop-25%39 citations
500. Causal Balancing for Domain GeneralizationPoster39 citations
501. Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear FunctionsTop-25%39 citations
502. Learning Zero-Shot Cooperation with Humans, Assuming Humans Are BiasedPoster39 citations
503. Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial ExamplesPoster39 citations
504. Multi-task Self-supervised Graph Neural Networks Enable Stronger Task GeneralizationPoster39 citations
505. REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPHTop-5%39 citations
506. Revisiting Graph Adversarial Attack and Defense From a Data Distribution PerspectivePoster39 citations
507. Rhino: Deep Causal Temporal Relationship Learning with History-dependent NoiseTop-25%39 citations
508. A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear ProgrammingPoster38 citations
509. Automated Data Augmentations for Graph ClassificationPoster38 citations
510. Benchmarking Offline Reinforcement Learning on Real-Robot HardwareTop-25%38 citations
511. CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement LearningPoster38 citations
512. Copy is All You NeedPoster38 citations
513. Disentanglement of Correlated Factors via Hausdorff Factorized SupportPoster38 citations
514. Efficient Deep Reinforcement Learning Requires Regulating OverfittingPoster38 citations
515. Interpretable Geometric Deep Learning via Learnable Randomness InjectionPoster38 citations
516. Learning Diffusion Bridges on Constrained DomainsTop-25%38 citations
517. Multimodal Analogical Reasoning over Knowledge GraphsPoster38 citations
518. Neural Causal Models for Counterfactual Identification and EstimationPoster38 citations
519. Packed Ensembles for efficient uncertainty estimationTop-25%38 citations
520. STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled TablesTop-25%38 citations
521. Searching Lottery Tickets in Graph Neural Networks: A Dual PerspectivePoster38 citations
522. Soft Neighbors are Positive Supporters in Contrastive Visual Representation LearningPoster38 citations
523. Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive OptimizationPoster38 citations
524. A General Framework for Sample-Efficient Function Approximation in Reinforcement LearningTop-25%37 citations
525. Beyond calibration: estimating the grouping loss of modern neural networksPoster37 citations
526. Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal PropagationPoster37 citations
527. Distilling Cognitive Backdoor Patterns within an ImagePoster37 citations
528. Logical Message Passing Networks with One-hop Inference on Atomic FormulasPoster37 citations
529. Multivariate Time-series Imputation with Disentangled Temporal RepresentationsPoster37 citations
530. Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population DynamicsTop-25%37 citations
531. Nonlinear Reconstruction for Operator Learning of PDEs with DiscontinuitiesTop-25%37 citations
532. Towards Robust Object Detection Invariant to Real-World Domain ShiftsPoster37 citations
533. DAG Matters! GFlowNets Enhanced Explainer for Graph Neural NetworksPoster36 citations
534. Diversify and Disambiguate: Out-of-Distribution Robustness via DisagreementPoster36 citations
535. EAGLE: Large-scale Learning of Turbulent Fluid Dynamics with Mesh TransformersPoster36 citations
536. Exploring Active 3D Object Detection from a Generalization PerspectiveTop-25%36 citations
537. GReTo: Remedying dynamic graph topology-task discordance via target homophilyPoster36 citations
538. HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained TransformersPoster36 citations
539. ISS: Image as Stepping Stone for Text-Guided 3D Shape GenerationTop-25%36 citations
540. Long-Tailed Partial Label Learning via Dynamic RebalancingPoster36 citations
541. MIMT: Masked Image Modeling Transformer for Video CompressionTop-25%36 citations
542. Machine Unlearning of Federated ClustersPoster36 citations
543. Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized ImagesTop-25%36 citations
544. Universal Few-shot Learning of Dense Prediction Tasks with Visual Token MatchingTop-5%36 citations
545. Which Layer is Learning Faster? A Systematic Exploration of Layer-wise Convergence Rate for Deep Neural NetworksPoster36 citations
546. (Certified!!) Adversarial Robustness for Free!Poster35 citations
547. A theoretical study of inductive biases in contrastive learningPoster35 citations
548. An Adaptive Policy to Employ Sharpness-Aware MinimizationPoster35 citations
549. Are More Layers Beneficial to Graph Transformers?Poster35 citations
550. Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial QueriesTop-25%35 citations
551. DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal SystemsTop-25%35 citations
552. Disentanglement with Biological Constraints: A Theory of Functional Cell TypesTop-25%35 citations
553. Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug DesignPoster35 citations
554. Fairness-aware Contrastive Learning with Partially Annotated Sensitive AttributesPoster35 citations
555. Learning Math Reasoning from Self-Sampled Correct and Partially-Correct SolutionsPoster35 citations
556. Learning differentiable solvers for systems with hard constraintsPoster35 citations
557. Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient DescentTop-25%35 citations
558. Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot LearningPoster35 citations
559. Mitigating Memorization of Noisy Labels via Regularization between RepresentationsPoster35 citations
560. No Reason for No Supervision: Improved Generalization in Supervised ModelsTop-25%35 citations
561. Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!Top-25%35 citations
562. Sparsity-Constrained Optimal TransportTop-25%35 citations
563. The Devil is in the Wrongly-classified Samples: Towards Unified Open-set RecognitionPoster35 citations
564. Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial RobustnessTop-5%34 citations
565. Backpropagation through Combinatorial Algorithms: Identity with Projection WorksPoster34 citations
566. Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation DetectionPoster34 citations
567. Compressing multidimensional weather and climate data into neural networksTop-5%34 citations
568. Defending against Adversarial Audio via Diffusion ModelPoster34 citations
569. Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual LearningPoster34 citations
570. FairGBM: Gradient Boosting with Fairness ConstraintsPoster34 citations
571. Fake It Until You Make It : Towards Accurate Near-Distribution Novelty DetectionPoster34 citations
572. Generating Diverse Cooperative Agents by Learning Incompatible PoliciesTop-25%34 citations
573. Indiscriminate Poisoning Attacks on Unsupervised Contrastive LearningTop-25%34 citations
574. Learning rigid dynamics with face interaction graph networksTop-25%34 citations
575. Model-based Causal Bayesian OptimizationTop-25%34 citations
576. NTK-SAP: Improving neural network pruning by aligning training dynamicsPoster34 citations
577. Online Bias Correction for Task-Free Continual LearningPoster34 citations
578. Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision ProcessesPoster34 citations
579. Planning Goals for ExplorationTop-25%34 citations
580. TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and SpecializationPoster34 citations
581. The Surprising Effectiveness of Equivariant Models in Domains with Latent SymmetryTop-25%34 citations
582. $\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function SpacePoster33 citations
583. Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World AttacksTop-25%33 citations
584. Benchmarking Constraint Inference in Inverse Reinforcement LearningPoster33 citations
585. Betty: An Automatic Differentiation Library for Multilevel OptimizationTop-5%33 citations
586. Composing Ensembles of Pre-trained Models via Iterative ConsensusPoster33 citations
587. Data Valuation Without Training of a ModelPoster33 citations
588. Investigating Multi-task Pretraining and Generalization in Reinforcement LearningPoster33 citations
589. Learning to Estimate Shapley Values with Vision TransformersTop-25%33 citations
590. LipsFormer: Introducing Lipschitz Continuity to Vision TransformersPoster33 citations
591. Lossless Adaptation of Pretrained Vision Models For Robotic ManipulationPoster33 citations
592. Neuro-Symbolic Procedural Planning with Commonsense PromptingTop-25%33 citations
593. One-Pixel Shortcut: On the Learning Preference of Deep Neural NetworksTop-25%33 citations
594. Perfectly Secure Steganography Using Minimum Entropy CouplingPoster33 citations
595. Solving stochastic weak Minty variational inequalities without increasing batch sizePoster33 citations
596. Spectral Decomposition Representation for Reinforcement LearningPoster33 citations
597. Sub-Task Decomposition Enables Learning in Sequence to Sequence TasksPoster33 citations
598. TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW RoutingPoster33 citations
599. Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple ObjectivesTop-5%33 citations
600. The Trade-off between Universality and Label Efficiency of Representations from Contrastive LearningTop-25%33 citations
601. Toeplitz Neural Network for Sequence ModelingTop-25%33 citations
602. Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal RetrievalPoster33 citations
603. FIGARO: Controllable Music Generation using Learned and Expert FeaturesPoster32 citations
604. Optimal Transport for Offline Imitation LearningTop-25%32 citations
605. Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex LossesPoster32 citations
606. The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich RegimesPoster32 citations
607. When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement LearningPoster32 citations
608. AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly DetectionPoster31 citations
609. CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous DrivingPoster31 citations
610. Denoising Diffusion Error Correction CodesTop-25%31 citations
611. Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline DataPoster31 citations
612. ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy RepresentationPoster31 citations
613. Emergence of Maps in the Memories of Blind Navigation AgentsTop-5%31 citations
614. Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient AlgorithmsTop-25%31 citations
615. Rethinking the Effect of Data Augmentation in Adversarial Contrastive LearningPoster31 citations
616. Revisiting Robustness in Graph Machine LearningPoster31 citations
617. SAM as an Optimal Relaxation of BayesTop-5%31 citations
618. SketchKnitter: Vectorized Sketch Generation with Diffusion ModelsTop-25%31 citations
619. Towards Open Temporal Graph Neural NetworksTop-5%31 citations
620. Autoregressive Conditional Neural ProcessesPoster30 citations
621. Become a Proficient Player with Limited Data through Watching Pure VideosPoster30 citations
622. Boosting Multiagent Reinforcement Learning via Permutation Invariant and Permutation Equivariant NetworksPoster30 citations
623. DBQ-SSD: Dynamic Ball Query for Efficient 3D Object DetectionPoster30 citations
624. Decision S4: Efficient Sequence-Based RL via State Spaces LayersPoster30 citations
625. Estimating individual treatment effects under unobserved confounding using binary instrumentsPoster30 citations
626. Explicitly Minimizing the Blur Error of Variational AutoencodersPoster30 citations
627. Fairness and Accuracy under Domain GeneralizationPoster30 citations
628. Federated Neural BanditsPoster30 citations
629. Hierarchical Relational Learning for Few-Shot Knowledge Graph CompletionPoster30 citations
630. HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetworkPoster30 citations
631. MMVAE+: Enhancing the Generative Quality of Multimodal VAEs without CompromisesPoster30 citations
632. Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto OptimalityPoster30 citations
633. ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual ActorPoster30 citations
634. Robust Fair Clustering: A Novel Fairness Attack and Defense FrameworkPoster30 citations
635. Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One ObjectivePoster30 citations
636. Symmetric Pruning in Quantum Neural NetworksTop-25%30 citations
637. Task Ambiguity in Humans and Language ModelsPoster30 citations
638. The Influence of Learning Rule on Representation Dynamics in Wide Neural NetworksTop-25%30 citations
639. TypeT5: Seq2seq Type Inference using Static AnalysisPoster30 citations
640. Understanding Influence Functions and Datamodels via Harmonic AnalysisPoster30 citations
641. Understanding Why Generalized Reweighting Does Not Improve Over ERMPoster30 citations
642. A Unified Framework for Soft Threshold PruningPoster29 citations
643. Avoiding spurious correlations via logit correctionPoster29 citations
644. Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian LearningPoster29 citations
645. Basic Binary Convolution Unit for Binarized Image Restoration NetworkPoster29 citations
646. Disparate Impact in Differential Privacy from Gradient MisalignmentTop-25%29 citations
647. FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image ClassificationPoster29 citations
648. Hierarchical Sliced Wasserstein DistancePoster29 citations
649. Incremental Learning of Structured Memory via Closed-Loop TranscriptionPoster29 citations
650. Learning to Decompose Visual Features with Latent Textual PromptsPoster29 citations
651. Learning to reason over visual objectsPoster29 citations
652. Metadata Archaeology: Unearthing Data Subsets by Leveraging Training DynamicsTop-25%29 citations
653. MocoSFL: enabling cross-client collaborative self-supervised learningTop-5%29 citations
654. On the Sensitivity of Reward Inference to Misspecified Human ModelsTop-5%29 citations
655. Order Matters: Agent-by-agent Policy OptimizationPoster29 citations
656. PerFedMask: Personalized Federated Learning with Optimized Masking VectorsPoster29 citations
657. Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst PathPoster29 citations
658. SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse EnvironmentsPoster29 citations
659. The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural NetworksTop-25%29 citations
660. TrojText: Test-time Invisible Textual Trojan InsertionPoster29 citations
661. Visually-Augmented Language ModelingPoster29 citations
662. Why (and When) does Local SGD Generalize Better than SGD?Poster29 citations
663. Your Contrastive Learning Is Secretly Doing Stochastic Neighbor EmbeddingPoster29 citations
664. Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant FunctionsPoster28 citations
665. DiffusER: Diffusion via Edit-based ReconstructionPoster28 citations
666. Diffusion Probabilistic FieldsPoster28 citations
667. From $t$-SNE to UMAP with contrastive learningPoster28 citations
668. Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory WeightingPoster28 citations
669. Hyperbolic Deep Reinforcement LearningTop-25%28 citations
670. Learning Soft Constraints From Constrained Expert DemonstrationsTop-25%28 citations
671. Modeling the Data-Generating Process is Necessary for Out-of-Distribution GeneralizationTop-25%28 citations
672. On amortizing convex conjugates for optimal transportPoster28 citations
673. Provable Memorization Capacity of TransformersPoster28 citations
674. Representational Dissimilarity Metric Spaces for Stochastic Neural NetworksPoster28 citations
675. Scaling Laws for a Multi-Agent Reinforcement Learning ModelPoster28 citations
676. Scaling Up Probabilistic Circuits by Latent Variable DistillationTop-5%28 citations
677. Stochastic Multi-Person 3D Motion ForecastingTop-25%28 citations
678. Transformer-based model for symbolic regression via joint supervised learningPoster28 citations
679. What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers?Poster28 citations
680. f-DM: A Multi-stage Diffusion Model via Progressive Signal TransformationPoster28 citations
681. Achieve the Minimum Width of Neural Networks for Universal ApproximationPoster27 citations
682. AutoGT: Automated Graph Transformer Architecture SearchTop-5%27 citations
683. CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled VideosPoster27 citations
684. Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?Poster27 citations
685. Deja Vu: Continual Model Generalization for Unseen DomainsPoster27 citations
686. Denoising Masked Autoencoders Help Robust ClassificationPoster27 citations
687. HotProtein: A Novel Framework for Protein Thermostability Prediction and EditingPoster27 citations
688. Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?Top-25%27 citations
689. LS-IQ: Implicit Reward Regularization for Inverse Reinforcement LearningPoster27 citations
690. Learning where and when to reason in neuro-symbolic inferenceTop-5%27 citations
691. Rethinking Graph Lottery Tickets: Graph Sparsity MattersPoster27 citations
692. STREET: A MULTI-TASK STRUCTURED REASONING AND EXPLANATION BENCHMARKTop-25%27 citations
693. Solving Continuous Control via Q-learningPoster27 citations
694. Unified Discrete Diffusion for Simultaneous Vision-Language GenerationPoster27 citations
695. Bias Propagation in Federated LearningPoster26 citations
696. Delving into Semantic Scale ImbalancePoster26 citations
697. Guiding continuous operator learning through Physics-based boundary constraintsPoster26 citations
698. Learning topology-preserving data representationsPoster26 citations
699. Mind the Gap: Offline Policy Optimization for Imperfect RewardsPoster26 citations
700. Multifactor Sequential Disentanglement via Structured Koopman AutoencodersTop-25%26 citations
701. Replicable BanditsPoster26 citations
702. Simplicial Hopfield networksPoster26 citations
703. Stable Target Field for Reduced Variance Score Estimation in Diffusion ModelsPoster26 citations
704. Temporal Dependencies in Feature Importance for Time Series PredictionPoster26 citations
705. The Power of Regularization in Solving Extensive-Form GamesPoster26 citations
706. Transformer Meets Boundary Value Inverse ProblemsPoster26 citations
707. CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated LearningPoster25 citations
708. Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?Poster25 citations
709. ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate RegretPoster25 citations
710. Efficient recurrent architectures through activity sparsity and sparse back-propagation through timeTop-25%25 citations
711. Fair Attribute Completion on Graph with Missing AttributesPoster25 citations
712. Latent Graph Inference using Product ManifoldsPoster25 citations
713. Link Prediction with Non-Contrastive LearningPoster25 citations
714. Measuring axiomatic soundness of counterfactual image modelsPoster25 citations
715. NTFields: Neural Time Fields for Physics-Informed Robot Motion PlanningTop-25%25 citations
716. NeRN: Learning Neural Representations for Neural NetworksTop-25%25 citations
717. Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill DiscoveryTop-25%25 citations
718. On the Saturation Effect of Kernel Ridge RegressionPoster25 citations
719. Predictive Inference with Feature Conformal PredictionPoster25 citations
720. SIMPLE: A Gradient Estimator for k-Subset SamplingPoster25 citations
721. Towards Better Selective ClassificationPoster25 citations
722. Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive LearningTop-25%25 citations
723. Voint Cloud: Multi-View Point Cloud Representation for 3D UnderstandingPoster25 citations
724. What shapes the loss landscape of self supervised learning?Poster25 citations
725. A Closer Look at Model Adaptation using Feature Distortion and Simplicity BiasTop-25%24 citations
726. Choreographer: Learning and Adapting Skills in ImaginationTop-25%24 citations
727. Continuous-time identification of dynamic state-space models by deep subspace encodingPoster24 citations
728. DaxBench: Benchmarking Deformable Object Manipulation with Differentiable PhysicsTop-5%24 citations
729. Deconstructing Distributions: A Pointwise Framework of LearningPoster24 citations
730. Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and RegularizationPoster24 citations
731. Dual Algorithmic ReasoningTop-25%24 citations
732. Evaluating Long-Term Memory in 3D MazesPoster24 citations
733. Function-Consistent Feature DistillationPoster24 citations
734. IDEAL: Query-Efficient Data-Free Learning from Black-Box ModelsPoster24 citations
735. Image to Sphere: Learning Equivariant Features for Efficient Pose PredictionTop-5%24 citations
736. Kernel Neural Optimal TransportPoster24 citations
737. Learnable Graph Convolutional Attention NetworksPoster24 citations
738. Learning What and Where: Disentangling Location and Identity Tracking Without SupervisionPoster24 citations
739. ManyDG: Many-domain Generalization for Healthcare ApplicationsPoster24 citations
740. Memory Gym: Partially Observable Challenges to Memory-Based AgentsPoster24 citations
741. Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNNPoster24 citations
742. Multi-domain image generation and translation with identifiability guaranteesTop-25%24 citations
743. Online Boundary-Free Continual Learning by Scheduled Data PriorPoster24 citations
744. Protein Representation Learning via Knowledge Enhanced Primary Structure ReasoningPoster24 citations
745. Re-weighting Based Group Fairness Regularization via Classwise Robust OptimizationPoster24 citations
746. Sampling-based inference for large linear models, with application to linearised LaplacePoster24 citations
747. Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the WildPoster24 citations
748. Suppressing the Heterogeneity: A Strong Feature Extractor for Few-shot SegmentationPoster24 citations
749. Tailoring Language Generation Models under Total Variation DistanceTop-5%24 citations
750. Agent-based Graph Neural NetworksPoster23 citations
751. Alternating Differentiation for Optimization LayersPoster23 citations
752. Asynchronous Distributed Bilevel OptimizationPoster23 citations
753. BSTT: A Bayesian Spatial-Temporal Transformer for Sleep StagingPoster23 citations
754. Causality Compensated Attention for Contextual Biased Visual RecognitionPoster23 citations
755. Characterizing the Influence of Graph ElementsPoster23 citations
756. Confidence-Conditioned Value Functions for Offline Reinforcement LearningTop-5%23 citations
757. Dual Student Networks for Data-Free Model StealingPoster23 citations
758. Efficiently Computing Nash Equilibria in Adversarial Team Markov GamesTop-5%23 citations
759. First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen DomainsPoster23 citations
760. Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descentTop-25%23 citations
761. Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient RepresentationsPoster23 citations
762. Learning Multimodal Data Augmentation in Feature SpacePoster23 citations
763. Learning to CROSS exchange to solve min-max vehicle routing problemsPoster23 citations
764. Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice PolytopesPoster23 citations
765. Maximizing Communication Efficiency for Large-scale Training via 0/1 AdamPoster23 citations
766. Mitigating Dataset Bias by Using Per-Sample GradientPoster23 citations
767. On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning.Poster23 citations
768. Progressive Voronoi Diagram Subdivision Enables Accurate Data-free Class-Incremental LearningPoster23 citations
769. Self-Ensemble Protection: Training Checkpoints Are Good Data ProtectorsPoster23 citations
770. Symmetries, Flat Minima, and the Conserved Quantities of Gradient FlowPoster23 citations
771. Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement LearningPoster23 citations
772. Towards Addressing Label Skews in One-Shot Federated LearningPoster23 citations
773. Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream TasksPoster23 citations
774. Unsupervised Learning for Combinatorial Optimization Needs Meta LearningPoster23 citations
775. Weighted Ensemble Self-Supervised LearningPoster23 citations
776. $O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov GamesPoster22 citations
777. $\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among CellsPoster22 citations
778. A CMDP-within-online framework for Meta-Safe Reinforcement LearningTop-25%22 citations
779. Actionable Neural Representations: Grid Cells from Minimal ConstraintsPoster22 citations
780. ChordMixer: A Scalable Neural Attention Model for Sequences with Different LengthPoster22 citations
781. CoRTX: Contrastive Framework for Real-time ExplanationPoster22 citations
782. Confidential-PROFITT: Confidential PROof of FaIr Training of TreesTop-5%22 citations
783. Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual PretrainingPoster22 citations
784. Decompositional Generation Process for Instance-Dependent Partial Label LearningTop-25%22 citations
785. DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable PhysicsPoster22 citations
786. Distributionally Robust Post-hoc Classifiers under Prior ShiftsPoster22 citations
787. Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL RobustnessTop-5%22 citations
788. Efficient Edge Inference by Selective QueryPoster22 citations
789. Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue SystemsPoster22 citations
790. Faster federated optimization under second-order similarityPoster22 citations
791. Guiding Energy-based Models via Contrastive Latent VariablesTop-25%22 citations
792. Learnable Topological Features For Phylogenetic Inference via Graph Neural NetworksPoster22 citations
793. Learning Controllable Adaptive Simulation for Multi-resolution PhysicsTop-25%22 citations
794. Learning to Extrapolate: A Transductive ApproachPoster22 citations
795. Meta-Learning in GamesPoster22 citations
796. More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy FactorizationPoster22 citations
797. Over-Training with Mixup May Hurt GeneralizationPoster22 citations
798. PASHA: Efficient HPO and NAS with Progressive Resource AllocationPoster22 citations
799. PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANsPoster22 citations
800. Particle-based Variational Inference with Preconditioned Functional Gradient FlowPoster22 citations
801. PatchDCT: Patch Refinement for High Quality Instance SegmentationPoster22 citations
802. Quality-Similar Diversity via Population Based Reinforcement LearningPoster22 citations
803. Robust Explanation Constraints for Neural NetworksPoster22 citations
804. SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model CommunicationPoster22 citations
805. Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RLPoster22 citations
806. Self-Guided Noise-Free Data Generation for Efficient Zero-Shot LearningTop-25%22 citations
807. Softened Symbol Grounding for Neuro-symbolic SystemsPoster22 citations
808. Task-Aware Information Routing from Common Representation Space in Lifelong LearningPoster22 citations
809. TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven OptimizationPoster22 citations
810. Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential MechanismPoster22 citations
811. VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-SynthesisPoster22 citations
812. CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language AlignmentPoster21 citations
813. Certifiably Robust Policy Learning against Adversarial Multi-Agent CommunicationPoster21 citations
814. Chasing All-Round Graph Representation Robustness: Model, Training, and OptimizationPoster21 citations
815. Compositional Task Representations for Large Language ModelsPoster21 citations
816. Confidence-Based Feature Imputation for Graphs with Partially Known FeaturesPoster21 citations
817. Effective passive membership inference attacks in federated learning against overparameterized modelsPoster21 citations
818. Energy-Based Test Sample Adaptation for Domain GeneralizationPoster21 citations
819. Federated Learning as Variational Inference: A Scalable Expectation Propagation ApproachPoster21 citations
820. Few-shot Backdoor Attacks via Neural Tangent KernelsPoster21 citations
821. GAMR: A Guided Attention Model for (visual) ReasoningPoster21 citations
822. GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group PropagationTop-25%21 citations
823. Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot LearnersPoster21 citations
824. How robust is unsupervised representation learning to distribution shift?Poster21 citations
825. Imbalanced Semi-supervised Learning with Bias Adaptive ClassifierPoster21 citations
826. LDMIC: Learning-based Distributed Multi-view Image CodingPoster21 citations
827. Learning Vortex Dynamics for Fluid Inference and PredictionPoster21 citations
828. Learning with Logical Constraints but without Shortcut SatisfactionTop-25%21 citations
829. Multi-Rate VAE: Train Once, Get the Full Rate-Distortion CurveTop-5%21 citations
830. SMART: Sentences as Basic Units for Text EvaluationPoster21 citations
831. Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep NetworksPoster21 citations
832. Simple and Scalable Nearest Neighbor Machine TranslationPoster21 citations
833. Simplicial Embeddings in Self-Supervised Learning and Downstream ClassificationTop-25%21 citations
834. SmartFRZ: An Efficient Training Framework using Attention-Based Layer FreezingTop-25%21 citations
835. Task-customized Masked Autoencoder via Mixture of Cluster-conditional ExpertsTop-25%21 citations
836. Training language models to summarize narratives improves brain alignmentTop-25%21 citations
837. Transfer NAS with Meta-learned Bayesian SurrogatesTop-5%21 citations
838. Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamicsPoster21 citations
839. Unsupervised visualization of image datasets using contrastive learningPoster21 citations
840. Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate DiffusionsPoster21 citations
841. Words are all you need? Language as an approximation for human similarity judgmentsPoster21 citations
842. A Message Passing Perspective on Learning Dynamics of Contrastive LearningPoster20 citations
843. Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide ImagesPoster20 citations
844. Bispectral Neural NetworksPoster20 citations
845. CFlowNets: Continuous Control with Generative Flow NetworksPoster20 citations
846. Conservative Bayesian Model-Based Value Expansion for Offline Policy OptimizationPoster20 citations
847. Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain AdaptationTop-25%20 citations
848. Efficient Conditionally Invariant Representation LearningTop-5%20 citations
849. Explaining Temporal Graph Models through an Explorer-Navigator FrameworkPoster20 citations
850. GOOD: Exploring geometric cues for detecting objects in an open worldPoster20 citations
851. How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated MoleculesPoster20 citations
852. Improved Convergence of Differential Private SGD with Gradient ClippingPoster20 citations
853. Instance-wise Batch Label Restoration via Gradients in Federated LearningPoster20 citations
854. Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural NetworksPoster20 citations
855. Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language ModelsTop-25%20 citations
856. KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong SignalsPoster20 citations
857. LMSeg: Language-guided Multi-dataset SegmentationPoster20 citations
858. Latent Bottlenecked Attentive Neural ProcessesPoster20 citations
859. Learning Hyper Label Model for Programmatic Weak SupervisionPoster20 citations
860. Learning the Positions in CountSketchTop-25%20 citations
861. MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerPoster20 citations
862. Near-optimal Coresets for Robust ClusteringTop-5%20 citations
863. On the Trade-Off between Actionable Explanations and the Right to be ForgottenPoster20 citations
864. Preserving Pre-trained Features Helps Calibrate Fine-tuned Language ModelsPoster20 citations
865. RLx2: Training a Sparse Deep Reinforcement Learning Model from ScratchTop-25%20 citations
866. Sampling-free Inference for Ab-Initio Potential Energy Surface NetworksPoster20 citations
867. Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) EquivariancePoster20 citations
868. Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated LearningPoster20 citations
869. Sparse Distributed Memory is a Continual LearnerPoster20 citations
870. Spatial Attention Kinetic Networks with E(n)-EquivariancePoster20 citations
871. Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic TasksPoster20 citations
872. View Synthesis with Sculpted Neural PointsTop-5%20 citations
873. WikiWhy: Answering and Explaining Cause-and-Effect QuestionsTop-5%20 citations
874. $\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural NetworksPoster19 citations
875. A Theoretical Framework for Inference and Learning in Predictive Coding NetworksPoster19 citations
876. Adversarial Diversity in HanabiTop-25%19 citations
877. Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GDPoster19 citations
878. Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's HypergradientsPoster19 citations
879. Certified Defences Against Adversarial Patch Attacks on Semantic SegmentationPoster19 citations
880. Concept Gradient: Concept-based Interpretation Without Linear AssumptionPoster19 citations
881. DCI-ES: An Extended Disentanglement Framework with Connections to IdentifiabilityPoster19 citations
882. Easy Differentially Private Linear RegressionPoster19 citations
883. Efficiently Controlling Multiple Risks with Pareto TestingPoster19 citations
884. Encoding Recurrence into TransformersTop-5%19 citations
885. FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced DataPoster19 citations
886. Hidden Markov Transformer for Simultaneous Machine TranslationTop-25%19 citations
887. Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance TomographyPoster19 citations
888. Learning Probabilistic Topological Representations Using Discrete Morse TheoryTop-25%19 citations
889. Learning a Data-Driven Policy Network for Pre-Training Automated Feature EngineeringTop-25%19 citations
890. Learning multi-scale local conditional probability models of imagesTop-25%19 citations
891. Meta Temporal Point ProcessesPoster19 citations
892. Neural Architecture Design and Robustness: A DatasetPoster19 citations
893. Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar ModelingPoster19 citations
894. Offline Reinforcement Learning with Differentiable Function Approximation is Provably EfficientPoster19 citations
895. Ollivier-Ricci Curvature for Hypergraphs: A Unified FrameworkPoster19 citations
896. Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation LearningPoster19 citations
897. ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on GraphsPoster19 citations
898. Scaling Laws For Deep Learning Based Image ReconstructionPoster19 citations
899. Summarization Programs: Interpretable Abstractive Summarization with Neural Modular TreesPoster19 citations
900. Understanding Embodied Reference with Touch-Line TransformerPoster19 citations
901. Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient AlgorithmsTop-5%19 citations
902. Write and Paint: Generative Vision-Language Models are Unified Modal LearnersPoster19 citations
903. A General Framework For Proving The Equivariant Strong Lottery Ticket HypothesisPoster18 citations
904. A Primal-Dual Framework for Transformers and Neural NetworksTop-25%18 citations
905. Accelerating Guided Diffusion Sampling with Splitting Numerical MethodsPoster18 citations
906. Computational Language Acquisition with Theory of MindPoster18 citations
907. Computing all Optimal Partial TransportsPoster18 citations
908. Consolidator: Mergable Adapter with Group Connections for Visual AdaptationPoster18 citations
909. Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?Poster18 citations
910. Discrete Predictor-Corrector Diffusion Models for Image SynthesisPoster18 citations
911. Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated SystemsTop-25%18 citations
912. Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded LossesPoster18 citations
913. Individual Privacy Accounting with Gaussian Differential PrivacyPoster18 citations
914. Is Forgetting Less a Good Inductive Bias for Forward Transfer?Poster18 citations
915. Learning to Segment from Noisy Annotations: A Spatial Correction ApproachPoster18 citations
916. Noise-Robust De-Duplication at ScalePoster18 citations
917. On Pre-training Language Model for AntibodyPoster18 citations
918. PV3D: A 3D Generative Model for Portrait Video GenerationPoster18 citations
919. Parallel Deep Neural Networks Have Zero Duality GapPoster18 citations
920. PowerQuant: Automorphism Search for Non-Uniform QuantizationPoster18 citations
921. Provable Defense Against Geometric TransformationsTop-25%18 citations
922. Recursive Time Series Data AugmentationPoster18 citations
923. Revisiting adapters with adversarial trainingTop-25%18 citations
924. Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense MechanismsPoster18 citations
925. Rotamer Density Estimator is an Unsupervised Learner of the Effect of Mutations on Protein-Protein InteractionPoster18 citations
926. Sampling with Mollified Interaction Energy DescentPoster18 citations
927. Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained CasePoster18 citations
928. Active Image IndexingPoster17 citations
929. Decoupled Training for Long-Tailed Classification With Stochastic RepresentationsPoster17 citations
930. Deep Reinforcement Learning for Cost-Effective Medical DiagnosisPoster17 citations
931. DiffMimic: Efficient Motion Mimicking with Differentiable PhysicsPoster17 citations
932. Distributed Differential Privacy in Multi-Armed BanditsPoster17 citations
933. Eva: Practical Second-order Optimization with Kronecker-vectorized ApproximationPoster17 citations
934. Evidential Uncertainty and Diversity Guided Active Learning for Scene Graph GenerationPoster17 citations
935. Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World DistributionsPoster17 citations
936. Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity GapPoster17 citations
937. How to prepare your task head for finetuningPoster17 citations
938. Information-Theoretic Analysis of Unsupervised Domain AdaptationPoster17 citations
939. Information-Theoretic DiffusionPoster17 citations
940. Interactive Portrait HarmonizationPoster17 citations
941. Koopman Neural Operator Forecaster for Time-series with Temporal Distributional ShiftsPoster17 citations
942. Latent Neural ODEs with Sparse Bayesian Multiple ShootingPoster17 citations
943. Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior SelectionTop-5%17 citations
944. Learning About Progress From ExpertsTop-25%17 citations
945. Learning Harmonic Molecular Representations on Riemannian ManifoldPoster17 citations
946. New Insights for the Stability-Plasticity Dilemma in Online Continual LearningPoster17 citations
947. PGrad: Learning Principal Gradients For Domain GeneralizationPoster17 citations
948. Proactive Multi-Camera Collaboration for 3D Human Pose EstimationPoster17 citations
949. Regression with Label Differential PrivacyPoster17 citations
950. Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function ApproximationPoster17 citations
951. Safe Reinforcement Learning From Pixels Using a Stochastic Latent RepresentationPoster17 citations
952. Stochastic Differentially Private and Fair LearningPoster17 citations
953. Temporal Coherent Test Time Optimization for Robust Video ClassificationPoster17 citations
954. The Provable Benefit of Unsupervised Data Sharing for Offline Reinforcement LearningPoster17 citations
955. Why adversarial training can hurt robust accuracyPoster17 citations
956. A Mixture-of-Expert Approach to RL-based Dialogue ManagementPoster16 citations
957. Bridge the Inference Gaps of Neural Processes via Expectation MaximizationPoster16 citations
958. ChiroDiff: Modelling chirographic data with Diffusion ModelsPoster16 citations
959. Decision Transformer under Random Frame DroppingPoster16 citations
960. DualAfford: Learning Collaborative Visual Affordance for Dual-gripper ManipulationPoster16 citations
961. Efficient Attention via Control VariatesTop-5%16 citations
962. EquiMod: An Equivariance Module to Improve Visual Instance DiscriminationPoster16 citations
963. ImaginaryNet: Learning Object Detectors without Real Images and AnnotationsPoster16 citations
964. Impossibly Good Experts and How to Follow ThemPoster16 citations
965. Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value FunctionPoster16 citations
966. Learning ReLU networks to high uniform accuracy is intractablePoster16 citations
967. Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuningPoster16 citations
968. Revisiting Intrinsic Reward for Exploration in Procedurally Generated EnvironmentsPoster16 citations
969. Single-shot General Hyper-parameter Optimization for Federated LearningTop-25%16 citations
970. Systematic Rectification of Language Models via Dead-end AnalysisPoster16 citations
971. Time to augment self-supervised visual representation learningPoster16 citations
972. Towards Smooth Video CompositionPoster16 citations
973. Valid P-Value for Deep Learning-driven Salient RegionPoster16 citations
974. A Stable and Scalable Method for Solving Initial Value PDEs with Neural NetworksPoster15 citations
975. AANG : Automating Auxiliary LearningTop-25%15 citations
976. Accurate Neural Training with 4-bit Matrix Multiplications at Standard FormatsPoster15 citations
977. Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by AggregationTop-5%15 citations
978. Cross-Layer Retrospective Retrieving via Layer AttentionPoster15 citations
979. DAVA: Disentangling Adversarial Variational AutoencoderPoster15 citations
980. Don’t fear the unlabelled: safe semi-supervised learning via debiasingPoster15 citations
981. Exploring The Role of Mean Teachers in Self-supervised Masked Auto-EncodersPoster15 citations
982. Feature selection and low test error in shallow low-rotation ReLU networksPoster15 citations
983. Few-shot Cross-domain Image Generation via Inference-time Latent-code LearningTop-25%15 citations
984. Fundamental Limits in Formal Verification of Message-Passing Neural NetworksPoster15 citations
985. Gromov-Wasserstein AutoencodersPoster15 citations
986. Is a Caption Worth a Thousand Images? A Study on Representation LearningPoster15 citations
987. Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary ClassificationTop-5%15 citations
988. Mutual Partial Label Learning with Competitive Label NoisePoster15 citations
989. On The Specialization of Neural ModulesPoster15 citations
990. Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised trainingPoster15 citations
991. Random Laplacian Features for Learning with Hyperbolic SpacePoster15 citations
992. Self-supervision through Random Segments with Autoregressive Coding (RandSAC)Poster15 citations
993. Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource DescriptionsPoster15 citations
994. Strategic Classification with Graph Neural NetworksPoster15 citations
995. The Tilted Variational Autoencoder: Improving Out-of-Distribution DetectionPoster15 citations
996. Towards Robustness Certification Against Universal PerturbationsPoster15 citations
997. User-Interactive Offline Reinforcement LearningPoster15 citations
998. Weakly-supervised HOI Detection via Prior-guided Bi-level Representation LearningPoster15 citations
999. Zeroth-Order Optimization with Trajectory-Informed Derivative EstimationPoster15 citations
1000. $\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural NetworksPoster14 citations

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