ICLR 2022 Accepted Papers

The full list of 1,094 papers accepted at ICLR 2022 (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. LoRA: Low-Rank Adaptation of Large Language ModelsPoster14,155 citations
2. Finetuned Language Models are Zero-Shot LearnersOral3,956 citations
3. BEiT: BERT Pre-Training of Image TransformersOral3,437 citations
4. Efficiently Modeling Long Sequences with Structured State SpacesOral2,281 citations
5. MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision TransformerPoster1,975 citations
6. Multitask Prompted Training Enables Zero-Shot Task GeneralizationSpotlight1,949 citations
7. How Attentive are Graph Attention Networks?Poster1,723 citations
8. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsPoster1,666 citations
9. Progressive Distillation for Fast Sampling of Diffusion ModelsSpotlight1,365 citations
10. VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised LearningPoster1,327 citations
11. Open-vocabulary Object Detection via Vision and Language Knowledge DistillationPoster1,091 citations
12. Towards a Unified View of Parameter-Efficient Transfer LearningSpotlight1,066 citations
13. DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRPoster1,046 citations
14. Image BERT Pre-training with Online TokenizerPoster1,044 citations
15. Offline Reinforcement Learning with Implicit Q-LearningPoster1,021 citations
16. Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and ForecastingOral984 citations
17. SimVLM: Simple Visual Language Model Pretraining with Weak SupervisionPoster918 citations
18. Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP FrameworkPoster825 citations
19. Fine-Tuning can Distort Pretrained Features and Underperform Out-of-DistributionOral807 citations
20. An Explanation of In-context Learning as Implicit Bayesian InferencePoster795 citations
21. Language-driven Semantic SegmentationPoster769 citations
22. Anomaly Transformer: Time Series Anomaly Detection with Association DiscrepancySpotlight768 citations
23. Train Short, Test Long: Attention with Linear Biases Enables Input Length ExtrapolationPoster757 citations
24. Perceiver IO: A General Architecture for Structured Inputs & OutputsSpotlight698 citations
25. How Do Vision Transformers Work?Spotlight687 citations
26. FILIP: Fine-grained Interactive Language-Image Pre-TrainingPoster672 citations
27. Tackling the Generative Learning Trilemma with Denoising Diffusion GANsSpotlight669 citations
28. Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution ShiftPoster667 citations
29. Pseudo Numerical Methods for Diffusion Models on ManifoldsPoster656 citations
30. StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image SynthesisPoster653 citations
31. GeoDiff: A Geometric Diffusion Model for Molecular Conformation GenerationOral645 citations
32. Label-Efficient Semantic Segmentation with Diffusion ModelsPoster644 citations
33. Solving Inverse Problems in Medical Imaging with Score-Based Generative ModelsPoster615 citations
34. Understanding over-squashing and bottlenecks on graphs via curvatureOral584 citations
35. Vector-quantized Image Modeling with Improved VQGANPoster575 citations
36. Open-Set Recognition: A Good Closed-Set Classifier is All You NeedOral556 citations
37. Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training ParadigmPoster535 citations
38. Fast Model Editing at ScalePoster510 citations
39. How Much Can CLIP Benefit Vision-and-Language Tasks?Poster494 citations
40. Omni-Dimensional Dynamic ConvolutionSpotlight472 citations
41. Understanding Dimensional Collapse in Contrastive Self-supervised LearningPoster452 citations
42. Graph Neural Networks with Learnable Structural and Positional RepresentationsPoster448 citations
43. Pre-training Molecular Graph Representation with 3D GeometryPoster443 citations
44. Large Language Models Can Be Strong Differentially Private LearnersOral415 citations
45. Pix2seq: A Language Modeling Framework for Object DetectionPoster415 citations
46. When Vision Transformers Outperform ResNets without Pre-training or Strong Data AugmentationsSpotlight410 citations
47. Differentially Private Fine-tuning of Language ModelsPoster403 citations
48. CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionPoster394 citations
49. Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement LearningPoster393 citations
50. VOS: Learning What You Don't Know by Virtual Outlier SynthesisPoster385 citations
51. Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic ModelsOral383 citations
52. Message Passing Neural PDE SolversSpotlight371 citations
53. Learning Audio-Visual Speech Representation by Masked Multimodal Cluster PredictionPoster368 citations
54. UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation LearningPoster364 citations
55. Is Homophily a Necessity for Graph Neural Networks?Poster358 citations
56. CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series ForecastingPoster354 citations
57. Gradient Matching for Domain GeneralizationPoster353 citations
58. On Bridging Generic and Personalized Federated Learning for Image ClassificationSpotlight344 citations
59. Temporal Efficient Training of Spiking Neural Network via Gradient Re-weightingPoster338 citations
60. Discovering Invariant Rationales for Graph Neural NetworksPoster332 citations
61. Trust Region Policy Optimisation in Multi-Agent Reinforcement LearningPoster329 citations
62. Unsupervised Semantic Segmentation by Distilling Feature CorrespondencesPoster328 citations
63. Large-Scale Representation Learning on Graphs via BootstrappingPoster324 citations
64. Crystal Diffusion Variational Autoencoder for Periodic Material GenerationPoster315 citations
65. Learning with Noisy Labels Revisited: A Study Using Real-World Human AnnotationsPoster313 citations
66. CDTrans: Cross-domain Transformer for Unsupervised Domain AdaptationPoster310 citations
67. FedBABU: Toward Enhanced Representation for Federated Image ClassificationPoster306 citations
68. Memorizing TransformersSpotlight302 citations
69. 8-bit Optimizers via Block-wise QuantizationSpotlight293 citations
70. cosFormer: Rethinking Softmax In AttentionPoster290 citations
71. Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural NetworksPoster280 citations
72. A Fine-Grained Analysis on Distribution ShiftOral272 citations
73. ViTGAN: Training GANs with Vision TransformersSpotlight269 citations
74. Geometric and Physical Quantities improve E(3) Equivariant Message PassingSpotlight268 citations
75. Score-Based Generative Modeling with Critically-Damped Langevin DiffusionSpotlight268 citations
76. Equivariant Transformers for Neural Network based Molecular PotentialsSpotlight265 citations
77. TAPEX: Table Pre-training via Learning a Neural SQL ExecutorPoster260 citations
78. Graph-less Neural Networks: Teaching Old MLPs New Tricks Via DistillationPoster258 citations
79. AS-MLP: An Axial Shifted MLP Architecture for VisionPoster256 citations
80. RegionViT: Regional-to-Local Attention for Vision TransformersPoster256 citations
81. Synchromesh: Reliable Code Generation from Pre-trained Language ModelsPoster255 citations
82. Uncertainty Modeling for Out-of-Distribution GeneralizationPoster252 citations
83. New Insights on Reducing Abrupt Representation Change in Online Continual LearningPoster251 citations
84. Open-World Semi-Supervised LearningPoster251 citations
85. Efficient Self-supervised Vision Transformers for Representation LearningPoster245 citations
86. Handling Distribution Shifts on Graphs: An Invariance PerspectivePoster245 citations
87. Conditional Object-Centric Learning from VideoPoster239 citations
88. PolyLoss: A Polynomial Expansion Perspective of Classification Loss FunctionsPoster239 citations
89. The Role of Permutation Invariance in Linear Mode Connectivity of Neural NetworksPoster237 citations
90. Equivariant Subgraph Aggregation NetworksSpotlight234 citations
91. Generating Videos with Dynamics-aware Implicit Generative Adversarial NetworksPoster234 citations
92. Adversarial Unlearning of Backdoors via Implicit HypergradientPoster233 citations
93. Backdoor Defense via Decoupling the Training ProcessPoster233 citations
94. Maximum Entropy RL (Provably) Solves Some Robust RL ProblemsPoster228 citations
95. Spherical Message Passing for 3D Molecular GraphsPoster228 citations
96. RvS: What is Essential for Offline RL via Supervised Learning?Poster227 citations
97. Sparse DETR: Efficient End-to-End Object Detection with Learnable SparsityPoster227 citations
98. ExT5: Towards Extreme Multi-Task Scaling for Transfer LearningPoster222 citations
99. Differentiable Prompt Makes Pre-trained Language Models Better Few-shot LearnersPoster220 citations
100. Scarf: Self-Supervised Contrastive Learning using Random Feature CorruptionSpotlight215 citations
101. Quadtree Attention for Vision TransformersPoster211 citations
102. From Stars to Subgraphs: Uplifting Any GNN with Local Structure AwarenessPoster210 citations
103. Graph Condensation for Graph Neural NetworksPoster206 citations
104. Effect of scale on catastrophic forgetting in neural networksPoster204 citations
105. Self-supervised Learning is More Robust to Dataset ImbalanceSpotlight204 citations
106. AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain AdaptationPoster203 citations
107. Transformers Can Do Bayesian InferencePoster202 citations
108. Poisoning and Backdooring Contrastive LearningOral201 citations
109. Learning Fast Samplers for Diffusion Models by Differentiating Through Sample QualityPoster200 citations
110. Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning SystemPoster196 citations
111. The Effects of Reward Misspecification: Mapping and Mitigating Misaligned ModelsPoster196 citations
112. Surrogate Gap Minimization Improves Sharpness-Aware TrainingPoster195 citations
113. Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion PredictionSpotlight192 citations
114. QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training QuantizationPoster192 citations
115. Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement LearningSpotlight191 citations
116. Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural NetworksPoster190 citations
117. PiCO: Contrastive Label Disambiguation for Partial Label LearningOral190 citations
118. Independent SE(3)-Equivariant Models for End-to-End Rigid Protein DockingSpotlight188 citations
119. Transformer-based Transform CodingPoster187 citations
120. THOMAS: Trajectory Heatmap Output with learned Multi-Agent SamplingPoster184 citations
121. You are AllSet: A Multiset Function Framework for Hypergraph Neural NetworksPoster184 citations
122. miniF2F: a cross-system benchmark for formal Olympiad-level mathematicsPoster184 citations
123. Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs TheoryPoster181 citations
124. Online Coreset Selection for Rehearsal-based Continual LearningPoster180 citations
125. Latent Image Animator: Learning to Animate Images via Latent Space NavigationPoster178 citations
126. Bayesian Neural Network Priors RevisitedPoster177 citations
127. Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?Poster177 citations
128. Byzantine-Robust Learning on Heterogeneous Datasets via BucketingSpotlight175 citations
129. Representational Continuity for Unsupervised Continual LearningOral174 citations
130. FILM: Following Instructions in Language with Modular MethodsPoster173 citations
131. FastSHAP: Real-Time Shapley Value EstimationPoster172 citations
132. Label Leakage and Protection in Two-party Split LearningPoster172 citations
133. Representation Learning for Online and Offline RL in Low-rank MDPsSpotlight172 citations
134. Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central PathOral171 citations
135. Pessimistic Model-based Offline Reinforcement Learning under Partial CoveragePoster171 citations
136. Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified ModelsPoster171 citations
137. Scale Efficiently: Insights from Pretraining and Finetuning TransformersPoster170 citations
138. Entroformer: A Transformer-based Entropy Model for Learned Image CompressionPoster169 citations
139. Sample and Computation Redistribution for Efficient Face DetectionPoster169 citations
140. Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to PracticePoster168 citations
141. Charformer: Fast Character Transformers via Gradient-based Subword TokenizationPoster168 citations
142. Leveraging unlabeled data to predict out-of-distribution performancePoster168 citations
143. Mapping Language Models to Grounded Conceptual SpacesPoster168 citations
144. Omni-Scale CNNs: a simple and effective kernel size configuration for time series classificationPoster168 citations
145. Autoregressive Diffusion ModelsPoster165 citations
146. Efficient Sharpness-aware Minimization for Improved Training of Neural NetworksPoster165 citations
147. Towards Continual Knowledge Learning of Language ModelsPoster165 citations
148. Bootstrapping Semantic Segmentation with Regional ContrastPoster163 citations
149. FedPara: Low-rank Hadamard Product for Communication-Efficient Federated LearningPoster162 citations
150. Domino: Discovering Systematic Errors with Cross-Modal EmbeddingsOral160 citations
151. Global Convergence of Multi-Agent Policy Gradient in Markov Potential GamesPoster160 citations
152. Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-designSpotlight160 citations
153. Illiterate DALL-E Learns to ComposePoster159 citations
154. Sample Selection with Uncertainty of Losses for Learning with Noisy LabelsPoster159 citations
155. Generative Models as a Data Source for Multiview Representation LearningPoster158 citations
156. Node Feature Extraction by Self-Supervised Multi-scale Neighborhood PredictionPoster157 citations
157. Equivariant and Stable Positional Encoding for More Powerful Graph Neural NetworksPoster155 citations
158. On the Connection between Local Attention and Dynamic Depth-wise ConvolutionSpotlight155 citations
159. A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud CompletionPoster153 citations
160. CKConv: Continuous Kernel Convolution For Sequential DataPoster153 citations
161. Graph-Guided Network for Irregularly Sampled Multivariate Time SeriesPoster153 citations
162. Frame Averaging for Invariant and Equivariant Network DesignOral152 citations
163. Benchmarking the Spectrum of Agent CapabilitiesPoster151 citations
164. Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure AnalysisPoster150 citations
165. On the Importance of Difficulty Calibration in Membership Inference AttacksPoster148 citations
166. Diverse Client Selection for Federated Learning via Submodular MaximizationPoster147 citations
167. Simple GNN Regularisation for 3D Molecular Property Prediction and BeyondPoster147 citations
168. Assessing Generalization of SGD via DisagreementSpotlight145 citations
169. Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation OverlapPoster145 citations
170. Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling SchemeOral145 citations
171. Extending the WILDS Benchmark for Unsupervised AdaptationOral143 citations
172. GiraffeDet: A Heavy-Neck Paradigm for Object DetectionPoster143 citations
173. Cold Brew: Distilling Graph Node Representations with Incomplete or Missing NeighborhoodsPoster142 citations
174. Memory Replay with Data Compression for Continual LearningPoster142 citations
175. Taming Sparsely Activated Transformer with Stochastic ExpertsPoster142 citations
176. Efficient Active Search for Combinatorial Optimization ProblemsPoster141 citations
177. Topological Graph Neural NetworksPoster141 citations
178. PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive PriorPoster140 citations
179. Complete Verification via Multi-Neuron Relaxation Guided Branch-and-BoundPoster138 citations
180. Exploring the Limits of Large Scale Pre-trainingSpotlight138 citations
181. Hyperparameter Tuning with Renyi Differential PrivacyOral138 citations
182. Leveraging Automated Unit Tests for Unsupervised Code TranslationSpotlight137 citations
183. BiBERT: Accurate Fully Binarized BERTPoster134 citations
184. Einops: Clear and Reliable Tensor Manipulations with Einstein-like NotationOral134 citations
185. Gradient Step Denoiser for convergent Plug-and-PlayPoster134 citations
186. Natural Language Descriptions of Deep Visual FeaturesOral134 citations
187. The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse TrainingPoster134 citations
188. Unified Visual Transformer CompressionPoster133 citations
189. On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural NetworksPoster131 citations
190. Dropout Q-Functions for Doubly Efficient Reinforcement LearningPoster130 citations
191. Proof Artifact Co-Training for Theorem Proving with Language ModelsPoster130 citations
192. A Program to Build E(N)-Equivariant Steerable CNNsPoster129 citations
193. The Efficiency MisnomerPoster128 citations
194. Adversarial Retriever-Ranker for Dense Text RetrievalPoster127 citations
195. A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"Oral126 citations
196. MT3: Multi-Task Multitrack Music TranscriptionSpotlight126 citations
197. Understanding and Preventing Capacity Loss in Reinforcement LearningSpotlight126 citations
198. BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation ModelsPoster125 citations
199. Divergence-aware Federated Self-Supervised LearningPoster125 citations
200. Unsupervised Discovery of Object Radiance FieldsPoster125 citations
201. Generalized Decision Transformer for Offline Hindsight Information MatchingSpotlight124 citations
202. GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node ClassificationPoster124 citations
203. When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?Poster124 citations
204. Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time SeriesSpotlight122 citations
205. What Happens after SGD Reaches Zero Loss? --A Mathematical FrameworkSpotlight122 citations
206. MonoDistill: Learning Spatial Features for Monocular 3D Object DetectionPoster120 citations
207. Salient ImageNet: How to discover spurious features in Deep Learning?Poster120 citations
208. Anomaly Detection for Tabular Data with Internal Contrastive LearningPoster119 citations
209. ViDT: An Efficient and Effective Fully Transformer-based Object DetectorPoster119 citations
210. NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge GraphsPoster118 citations
211. OntoProtein: Protein Pretraining With Gene Ontology EmbeddingPoster118 citations
212. Post hoc Explanations may be Ineffective for Detecting Unknown Spurious CorrelationPoster118 citations
213. RotoGrad: Gradient Homogenization in Multitask LearningSpotlight118 citations
214. Understanding Domain Randomization for Sim-to-real TransferSpotlight118 citations
215. Accelerated Policy Learning with Parallel Differentiable SimulationPoster116 citations
216. Invariant Causal Representation Learning for Out-of-Distribution GeneralizationPoster116 citations
217. Predicting Physics in Mesh-reduced Space with Temporal AttentionPoster116 citations
218. Path Integral Sampler: A Stochastic Control Approach For SamplingPoster115 citations
219. Language model compression with weighted low-rank factorizationPoster113 citations
220. Responsible Disclosure of Generative Models Using Scalable FingerprintingSpotlight113 citations
221. SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement LearningPoster113 citations
222. Step-unrolled Denoising Autoencoders for Text GenerationPoster113 citations
223. Understanding and Improving Graph Injection Attack by Promoting UnnoticeabilityPoster113 citations
224. On Improving Adversarial Transferability of Vision TransformersSpotlight112 citations
225. ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit SimilarityPoster111 citations
226. Efficient Token Mixing for Transformers via Adaptive Fourier Neural OperatorsPoster110 citations
227. Relating transformers to models and neural representations of the hippocampal formationPoster110 citations
228. Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal TransformersSpotlight109 citations
229. Coordination Among Neural Modules Through a Shared Global WorkspaceOral108 citations
230. TRGP: Trust Region Gradient Projection for Continual LearningSpotlight108 citations
231. LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5Poster107 citations
232. Neural Networks as Kernel Learners: The Silent Alignment EffectPoster107 citations
233. Learning to Extend Molecular Scaffolds with Structural MotifsPoster106 citations
234. Adversarial Robustness Through the Lens of CausalityPoster105 citations
235. DemoDICE: Offline Imitation Learning with Supplementary Imperfect DemonstrationsPoster105 citations
236. Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute EstimationPoster105 citations
237. An Autoregressive Flow Model for 3D Molecular Geometry Generation from ScratchPoster104 citations
238. FlexConv: Continuous Kernel Convolutions With Differentiable Kernel SizesPoster104 citations
239. Learning Optimal Conformal ClassifiersSpotlight104 citations
240. Scaling Laws for Neural Machine TranslationSpotlight104 citations
241. VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated ObjectsPoster104 citations
242. Pretrained Language Model in Continual Learning: A Comparative StudyPoster101 citations
243. MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training ConflictsPoster100 citations
244. What Do We Mean by Generalization in Federated Learning?Poster100 citations
245. An Unconstrained Layer-Peeled Perspective on Neural CollapsePoster99 citations
246. Automated Self-Supervised Learning for GraphsPoster99 citations
247. On the Role of Neural Collapse in Transfer LearningPoster99 citations
248. Graph Neural Network Guided Local Search for the Traveling Salesperson ProblemPoster98 citations
249. How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive LearningPoster98 citations
250. NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet TrainingPoster98 citations
251. NODE-GAM: Neural Generalized Additive Model for Interpretable Deep LearningSpotlight98 citations
252. Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-offPoster98 citations
253. MetaMorph: Learning Universal Controllers with TransformersPoster97 citations
254. The MultiBERTs: BERT Reproductions for Robustness AnalysisSpotlight97 citations
255. Expressiveness and Approximation Properties of Graph Neural NetworksOral96 citations
256. GRAND++: Graph Neural Diffusion with A Source TermPoster96 citations
257. Learning Temporally Causal Latent Processes from General Temporal DataPoster95 citations
258. Pareto Set Learning for Neural Multi-Objective Combinatorial OptimizationPoster95 citations
259. Decoupled Adaptation for Cross-Domain Object DetectionPoster94 citations
260. Exploring Memorization in Adversarial TrainingPoster94 citations
261. Learning to Map for Active Semantic Goal NavigationPoster94 citations
262. Reliable Adversarial Distillation with Unreliable TeachersPoster93 citations
263. Reward Uncertainty for Exploration in Preference-based Reinforcement LearningPoster93 citations
264. Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial LearningPoster93 citations
265. ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of MindPoster93 citations
266. AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value AnalysisPoster92 citations
267. Differentiable Scaffolding Tree for Molecule OptimizationPoster92 citations
268. Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?Poster92 citations
269. Subspace Regularizers for Few-Shot Class Incremental LearningPoster92 citations
270. Emergent Communication at ScaleSpotlight91 citations
271. Equivariant Graph Mechanics Networks with ConstraintsPoster91 citations
272. InfinityGAN: Towards Infinite-Pixel Image SynthesisPoster90 citations
273. Stochastic Training is Not Necessary for GeneralizationPoster90 citations
274. Chemical-Reaction-Aware Molecule Representation LearningPoster89 citations
275. Neural Contextual Bandits with Deep Representation and Shallow ExplorationPoster89 citations
276. Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network ModelsSpotlight89 citations
277. Policy improvement by planning with GumbelSpotlight89 citations
278. Optimal Representations for Covariate ShiftPoster88 citations
279. PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature CommunicationPoster88 citations
280. Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS BenchmarksPoster88 citations
281. Zero-Shot Self-Supervised Learning for MRI ReconstructionPoster88 citations
282. Mirror Descent Policy OptimizationPoster87 citations
283. Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with PessimismPoster87 citations
284. Efficient Neural Causal Discovery without Acyclicity ConstraintsPoster86 citations
285. Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RLPoster86 citations
286. TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series ForecastingSpotlight86 citations
287. Attention-based Interpretability with Concept TransformersPoster85 citations
288. Planning in Stochastic Environments with a Learned ModelSpotlight85 citations
289. BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech SynthesisPoster84 citations
290. Generative Modeling with Optimal Transport MapsPoster84 citations
291. HTLM: Hyper-Text Pre-Training and Prompting of Language ModelsPoster84 citations
292. Bootstrapped Meta-LearningOral83 citations
293. Generalized Demographic Parity for Group FairnessPoster83 citations
294. Model Zoo: A Growing Brain That Learns ContinuallyPoster83 citations
295. Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family DistributionsSpotlight83 citations
296. Neural Link Prediction with Walk PoolingPoster83 citations
297. Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime InferencePoster83 citations
298. Reinforcement Learning with Sparse Rewards using Guidance from Offline DemonstrationSpotlight83 citations
299. Revisiting Over-smoothing in BERT from the Perspective of GraphSpotlight83 citations
300. SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian ApproximationPoster83 citations
301. An Agnostic Approach to Federated Learning with Class ImbalancePoster82 citations
302. Chunked Autoregressive GAN for Conditional Waveform SynthesisPoster82 citations
303. Incremental False Negative Detection for Contrastive LearningPoster82 citations
304. Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial NetworksPoster82 citations
305. Visual Representation Learning Does Not Generalize Strongly Within the Same DomainPoster81 citations
306. $\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian OptimizationPoster80 citations
307. AdaRL: What, Where, and How to Adapt in Transfer Reinforcement LearningSpotlight79 citations
308. Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLPoster79 citations
309. Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular DesignSpotlight78 citations
310. DEPTS: Deep Expansion Learning for Periodic Time Series ForecastingSpotlight78 citations
311. Vitruvion: A Generative Model of Parametric CAD SketchesPoster78 citations
312. Discovering Latent Concepts Learned in BERTPoster77 citations
313. ZeroFL: Efficient On-Device Training for Federated Learning with Local SparsityPoster77 citations
314. DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNSOral76 citations
315. Continual Normalization: Rethinking Batch Normalization for Online Continual LearningPoster74 citations
316. Few-Shot Backdoor Attacks on Visual Object TrackingPoster74 citations
317. Graph Auto-Encoder via Neighborhood Wasserstein ReconstructionPoster74 citations
318. Resolving Training Biases via Influence-based Data RelabelingOral74 citations
319. Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100Spotlight73 citations
320. Towards Model Agnostic Federated Learning Using Knowledge DistillationPoster73 citations
321. A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed FeaturesPoster72 citations
322. Learning Strides in Convolutional Neural NetworksOral72 citations
323. Lipschitz-constrained Unsupervised Skill DiscoveryPoster72 citations
324. No One Representation to Rule Them All: Overlapping Features of Training MethodsPoster72 citations
325. TAda! Temporally-Adaptive Convolutions for Video UnderstandingPoster72 citations
326. Amortized Implicit Differentiation for Stochastic Bilevel OptimizationPoster71 citations
327. Source-Free Adaptation to Measurement Shift via Bottom-Up Feature RestorationSpotlight71 citations
328. Transferable Adversarial Attack based on Integrated GradientsPoster71 citations
329. DR3: Value-Based Deep Reinforcement Learning Requires Explicit RegularizationSpotlight70 citations
330. Revisiting Design Choices in Offline Model Based Reinforcement LearningSpotlight70 citations
331. Constrained Policy Optimization via Bayesian World ModelsSpotlight69 citations
332. GradMax: Growing Neural Networks using Gradient InformationPoster69 citations
333. HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action RepresentationPoster69 citations
334. Learning Efficient Image Super-Resolution Networks via Structure-Regularized PruningPoster69 citations
335. Learning Efficient Online 3D Bin Packing on Packing Configuration TreesPoster69 citations
336. Self-ensemble Adversarial Training for Improved RobustnessPoster69 citations
337. Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box DomainsPoster68 citations
338. Critical Points in Quantum Generative ModelsPoster68 citations
339. Efficient Split-Mix Federated Learning for On-Demand and In-Situ CustomizationPoster68 citations
340. EntQA: Entity Linking as Question AnsweringSpotlight68 citations
341. Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problemsSpotlight68 citations
342. Meta-Learning with Fewer Tasks through Task InterpolationOral68 citations
343. The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic GeneralizationPoster68 citations
344. EXACT: Scalable Graph Neural Networks Training via Extreme Activation CompressionPoster67 citations
345. MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical ModelingOral67 citations
346. COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction EstimationSpotlight66 citations
347. How to Train Your MAML to Excel in Few-Shot ClassificationPoster66 citations
348. Data Poisoning Won’t Save You From Facial RecognitionPoster65 citations
349. Do We Need Anisotropic Graph Neural Networks?Poster65 citations
350. Efficient Learning of Safe Driving Policy via Human-AI Copilot OptimizationPoster65 citations
351. Policy Smoothing for Provably Robust Reinforcement LearningPoster65 citations
352. Acceleration of Federated Learning with Alleviated Forgetting in Local TrainingPoster64 citations
353. DISSECT: Disentangled Simultaneous Explanations via Concept TraversalsPoster64 citations
354. DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with ToolsPoster64 citations
355. Fairness Guarantees under Demographic ShiftPoster64 citations
356. KL Guided Domain AdaptationPoster64 citations
357. RelaxLoss: Defending Membership Inference Attacks without Losing UtilitySpotlight64 citations
358. Skill-based Meta-Reinforcement LearningPoster64 citations
359. PSA-GAN: Progressive Self Attention GANs for Synthetic Time SeriesPoster63 citations
360. SphereFace2: Binary Classification is All You Need for Deep Face RecognitionSpotlight63 citations
361. Finding an Unsupervised Image Segmenter in each of your Deep Generative ModelsPoster62 citations
362. Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack ScenariosPoster62 citations
363. StyleAlign: Analysis and Applications of Aligned StyleGAN ModelsOral62 citations
364. Cross-Domain Imitation Learning via Optimal TransportPoster60 citations
365. Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic SparsityPoster60 citations
366. Dual Lottery Ticket HypothesisPoster60 citations
367. Hybrid Local SGD for Federated Learning with Heterogeneous CommunicationsSpotlight60 citations
368. On the Certified Robustness for Ensemble Models and BeyondPoster60 citations
369. Transformer Embeddings of Irregularly Spaced Events and Their ParticipantsPoster60 citations
370. Understanding the Role of Self Attention for Efficient Speech RecognitionSpotlight60 citations
371. Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a LoopPoster60 citations
372. Variational methods for simulation-based inferenceSpotlight60 citations
373. Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space PerspectivePoster60 citations
374. Wisdom of Committees: An Overlooked Approach To Faster and More Accurate ModelsPoster60 citations
375. CROP: Certifying Robust Policies for Reinforcement Learning through Functional SmoothingPoster59 citations
376. ConFeSS: A Framework for Single Source Cross-Domain Few-Shot LearningPoster59 citations
377. Consistent Counterfactuals for Deep ModelsPoster59 citations
378. Exploiting Class Activation Value for Partial-Label LearningPoster59 citations
379. GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue SystemsPoster59 citations
380. Learning Super-Features for Image RetrievalPoster59 citations
381. NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly EasyPoster59 citations
382. ComPhy: Compositional Physical Reasoning of Objects and Events from VideosPoster58 citations
383. Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--HastingsPoster58 citations
384. Towards General Function Approximation in Zero-Sum Markov GamesPoster58 citations
385. Bayesian Framework for Gradient LeakagePoster57 citations
386. Information-theoretic Online Memory Selection for Continual LearningPoster57 citations
387. Learning more skills through optimistic explorationSpotlight57 citations
388. Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax OptimalityPoster57 citations
389. TRAIL: Near-Optimal Imitation Learning with Suboptimal DataPoster57 citations
390. F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationOral56 citations
391. Hierarchical Few-Shot Imitation with Skill Transition ModelsPoster56 citations
392. On the Pitfalls of Analyzing Individual Neurons in Language ModelsPoster56 citations
393. Boosting Randomized Smoothing with Variance Reduced ClassifiersSpotlight55 citations
394. Fixed Neural Network Steganography: Train the images, not the networkPoster55 citations
395. Igeood: An Information Geometry Approach to Out-of-Distribution DetectionPoster55 citations
396. Large Learning Rate Tames Homogeneity: Convergence and Balancing EffectPoster55 citations
397. Learning to Complete Code with SketchesPoster55 citations
398. NASI: Label- and Data-agnostic Neural Architecture Search at InitializationPoster55 citations
399. Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability AuthorizationOral55 citations
400. Prospect Pruning: Finding Trainable Weights at Initialization using Meta-GradientsPoster55 citations
401. A Deep Variational Approach to Clustering Survival DataPoster54 citations
402. A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based ModelPoster54 citations
403. Defending Against Image Corruptions Through Adversarial AugmentationsPoster54 citations
404. Discrete Representations Strengthen Vision Transformer RobustnessPoster54 citations
405. Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical SolutionsSpotlight54 citations
406. Improving Non-Autoregressive Translation Models Without DistillationPoster54 citations
407. Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic ForecastingPoster54 citations
408. Long Expressive Memory for Sequence ModelingSpotlight54 citations
409. Programmatic Reinforcement Learning without OraclesSpotlight54 citations
410. Top-label calibration and multiclass-to-binary reductionsPoster54 citations
411. DKM: Differentiable k-Means Clustering Layer for Neural Network CompressionPoster53 citations
412. DeSKO: Stability-Assured Robust Control with a Deep Stochastic Koopman OperatorPoster53 citations
413. Federated Learning from Only Unlabeled Data with Class-conditional-sharing ClientsPoster53 citations
414. Mention Memory: incorporating textual knowledge into Transformers through entity mention attentionPoster53 citations
415. Modular Lifelong Reinforcement Learning via Neural CompositionPoster53 citations
416. Sample Efficient Deep Reinforcement Learning via Uncertainty EstimationSpotlight53 citations
417. Rethinking Supervised Pre-Training for Better Downstream TransferringPoster52 citations
418. Semi-relaxed Gromov-Wasserstein divergence and applications on graphsPoster52 citations
419. Trigger Hunting with a Topological Prior for Trojan DetectionPoster52 citations
420. A Unified Wasserstein Distributional Robustness Framework for Adversarial TrainingPoster51 citations
421. Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport DistillationPoster51 citations
422. Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial RobustnessPoster51 citations
423. Looking Back on Learned Experiences For Class/task Incremental LearningSpotlight51 citations
424. On Evaluation Metrics for Graph Generative ModelsPoster51 citations
425. Representing Mixtures of Word Embeddings with Mixtures of Topic EmbeddingsPoster51 citations
426. CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG SignalsPoster50 citations
427. How to deal with missing data in supervised deep learning?Poster50 citations
428. Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning ViewPoster50 citations
429. Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element NetworksSpotlight50 citations
430. Offline Reinforcement Learning with Value-based Episodic MemoryPoster50 citations
431. Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious CorrelationsPoster50 citations
432. What’s Wrong with Deep Learning in Tree Search for Combinatorial OptimizationPoster50 citations
433. Collapse by Conditioning: Training Class-conditional GANs with Limited DataPoster49 citations
434. High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad StepsizePoster49 citations
435. Hindsight: Posterior-guided training of retrievers for improved open-ended generationPoster49 citations
436. Learning 3D Representations of Molecular Chirality with Invariance to Bond RotationsPoster49 citations
437. A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural NetworksPoster48 citations
438. CURVATURE-GUIDED DYNAMIC SCALE NETWORKS FOR MULTI-VIEW STEREOPoster48 citations
439. DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement LearningPoster48 citations
440. Fortuitous Forgetting in Connectionist NetworksPoster48 citations
441. Neural Deep Equilibrium SolversPoster48 citations
442. Neural Methods for Logical Reasoning over Knowledge GraphsPoster48 citations
443. Vision-Based Manipulators Need to Also See from Their HandsOral48 citations
444. Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learningPoster48 citations
445. Data-Driven Offline Optimization for Architecting Hardware AcceleratorsPoster47 citations
446. Differentiable DAG SamplingPoster47 citations
447. Learned Simulators for TurbulencePoster47 citations
448. Learning to Downsample for Segmentation of Ultra-High Resolution ImagesPoster47 citations
449. Noisy Feature MixupPoster47 citations
450. Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency DetectionPoster47 citations
451. Regularized Autoencoders for Isometric Representation LearningPoster47 citations
452. Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent DesignOral47 citations
453. Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)Poster47 citations
454. Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave FunctionsSpotlight46 citations
455. CoBERL: Contrastive BERT for Reinforcement LearningSpotlight46 citations
456. CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain GeneralizationPoster46 citations
457. Deconstructing the Inductive Biases of Hamiltonian Neural NetworksSpotlight46 citations
458. Effective Model Sparsification by Scheduled Grow-and-Prune MethodsPoster46 citations
459. Improving Federated Learning Face Recognition via Privacy-Agnostic ClustersSpotlight46 citations
460. Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and BeyondOral46 citations
461. PAC Prediction Sets Under Covariate ShiftPoster46 citations
462. Revisiting flow generative models for Out-of-distribution detectionPoster46 citations
463. Sparsity Winning Twice: Better Robust Generalization from More Efficient TrainingPoster46 citations
464. An Information Fusion Approach to Learning with Instance-Dependent Label NoisePoster45 citations
465. Continual Learning with Recursive Gradient OptimizationSpotlight45 citations
466. EE-Net: Exploitation-Exploration Neural Networks in Contextual BanditsSpotlight45 citations
467. Fair Normalizing FlowsPoster45 citations
468. Learning Long-Term Reward Redistribution via Randomized Return DecompositionSpotlight45 citations
469. Learning-Augmented $k$-means ClusteringSpotlight45 citations
470. Low-Budget Active Learning via Wasserstein Distance: An Integer Programming ApproachPoster45 citations
471. Neural graphical modelling in continuous-time: consistency guarantees and algorithmsPoster45 citations
472. Objects in Semantic TopologyPoster45 citations
473. Data-Efficient Graph Grammar Learning for Molecular GenerationOral44 citations
474. Denoising Likelihood Score Matching for Conditional Score-based Data GenerationPoster44 citations
475. Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient DescentPoster44 citations
476. Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural NetworksPoster44 citations
477. Permutation Compressors for Provably Faster Distributed Nonconvex OptimizationPoster44 citations
478. Rethinking Adversarial Transferability from a Data Distribution PerspectivePoster44 citations
479. Should I Run Offline Reinforcement Learning or Behavioral Cloning?Poster44 citations
480. Adversarially Robust Conformal PredictionPoster43 citations
481. CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and ComparabilityPoster43 citations
482. FP-DETR: Detection Transformer Advanced by Fully Pre-trainingPoster43 citations
483. Learning Graphon Mean Field Games and Approximate Nash EquilibriaPoster43 citations
484. Learning by Directional Gradient DescentPoster43 citations
485. Meta Discovery: Learning to Discover Novel Classes given Very Limited DataSpotlight43 citations
486. On the Existence of Universal Lottery TicketsPoster43 citations
487. PAC-Bayes Information BottleneckSpotlight43 citations
488. Strength of Minibatch Noise in SGDSpotlight43 citations
489. Universalizing Weak SupervisionPoster43 citations
490. Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable RepresentationsPoster42 citations
491. Can an Image Classifier Suffice For Action Recognition?Poster42 citations
492. Enhancing Cross-lingual Transfer by Manifold MixupPoster42 citations
493. GLASS: GNN with Labeling Tricks for Subgraph Representation LearningPoster42 citations
494. Geometry-Consistent Neural Shape Representation with Implicit Displacement FieldsPoster42 citations
495. Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized TeamingPoster42 citations
496. A Loss Curvature Perspective on Training Instabilities of Deep Learning ModelsPoster41 citations
497. Explainable GNN-Based Models over Knowledge GraphsPoster41 citations
498. GNN is a Counter? Revisiting GNN for Question AnsweringPoster41 citations
499. Graph-Relational Domain AdaptationPoster41 citations
500. How to Robustify Black-Box ML Models? A Zeroth-Order Optimization PerspectiveSpotlight41 citations
501. Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No RetrainingSpotlight41 citations
502. Properties from mechanisms: an equivariance perspective on identifiable representation learningSpotlight41 citations
503. The Rich Get Richer: Disparate Impact of Semi-Supervised LearningPoster41 citations
504. Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon ReasoningPoster41 citations
505. You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory PredictionPoster41 citations
506. Context-Aware Sparse Deep Coordination GraphsSpotlight40 citations
507. Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit RegularizationPoster40 citations
508. Geometric Transformers for Protein Interface Contact PredictionPoster40 citations
509. How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean DataPoster40 citations
510. Language modeling via stochastic processesOral40 citations
511. Network Augmentation for Tiny Deep LearningPoster40 citations
512. On the Limitations of Multimodal VAEsPoster40 citations
513. SOSP: Efficiently Capturing Global Correlations by Second-Order Structured PruningSpotlight40 citations
514. The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human ModelsPoster40 citations
515. The Inductive Bias of In-Context Learning: Rethinking Pretraining Example DesignSpotlight40 citations
516. The Information Geometry of Unsupervised Reinforcement LearningOral40 citations
517. Top-N: Equivariant Set and Graph Generation without ExchangeabilityPoster40 citations
518. Discovering Nonlinear PDEs from Scarce Data with Physics-encoded LearningPoster39 citations
519. GATSBI: Generative Adversarial Training for Simulation-Based InferencePoster39 citations
520. GNN-LM: Language Modeling based on Global Contexts via GNNSpotlight39 citations
521. How Well Does Self-Supervised Pre-Training Perform with Streaming Data?Poster39 citations
522. Procedural generalization by planning with self-supervised world modelsPoster39 citations
523. The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal SolutionsOral39 citations
524. Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability PerspectiveSpotlight39 citations
525. When should agents explore?Spotlight39 citations
526. COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning AttacksPoster38 citations
527. Generalizing Few-Shot NAS with Gradient MatchingPoster38 citations
528. It Takes Two to Tango: Mixup for Deep Metric LearningPoster38 citations
529. Learning transferable motor skills with hierarchical latent mixture policiesSpotlight38 citations
530. Multi-Mode Deep Matrix and Tensor FactorizationPoster38 citations
531. On the role of population heterogeneity in emergent communicationPoster38 citations
532. Continual Learning with Filter Atom SwappingSpotlight37 citations
533. Deep Learning without Shortcuts: Shaping the Kernel with Tailored RectifiersPoster37 citations
534. Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANsPoster37 citations
535. Generalized Kernel ThinningPoster37 citations
536. GradSign: Model Performance Inference with Theoretical InsightsPoster37 citations
537. Group equivariant neural posterior estimationPoster37 citations
538. Learning to Generalize across Domains on Single Test SamplesPoster37 citations
539. Modeling Label Space Interactions in Multi-label Classification using Box EmbeddingsPoster37 citations
540. Revisit Kernel Pruning with Lottery Regulated Grouped ConvolutionsPoster37 citations
541. Sound Adversarial Audio-Visual NavigationPoster37 citations
542. Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement LearningPoster37 citations
543. Universal Approximation Under Constraints is Possible with TransformersSpotlight37 citations
544. An Experimental Design Perspective on Model-Based Reinforcement LearningPoster36 citations
545. Attacking deep networks with surrogate-based adversarial black-box methods is easyPoster36 citations
546. Auto-scaling Vision Transformers without TrainingPoster36 citations
547. Autonomous Reinforcement Learning: Formalism and BenchmarkingPoster36 citations
548. Compositional Training for End-to-End Deep AUC MaximizationSpotlight36 citations
549. Continuously Discovering Novel Strategies via Reward-Switching Policy OptimizationPoster36 citations
550. DEGREE: Decomposition Based Explanation for Graph Neural NetworksPoster36 citations
551. Knowledge Removal in Sampling-based Bayesian InferencePoster36 citations
552. MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without RetrainingPoster36 citations
553. Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillationsPoster36 citations
554. Who Is Your Right Mixup Partner in Positive and Unlabeled LearningPoster36 citations
555. Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and TransferablePoster35 citations
556. Boosting the Certified Robustness of L-infinity Distance NetsPoster35 citations
557. CrossBeam: Learning to Search in Bottom-Up Program SynthesisPoster35 citations
558. Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting DistributionsPoster35 citations
559. Increasing the Cost of Model Extraction with Calibrated Proof of WorkSpotlight35 citations
560. SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit modelsSpotlight35 citations
561. Selective Ensembles for Consistent PredictionsPoster35 citations
562. Triangle and Four Cycle Counting with Predictions in Graph StreamsPoster35 citations
563. Comparing Distributions by Measuring Differences that Affect Decision MakingOral34 citations
564. Conditional Image Generation by Conditioning Variational Auto-EncodersPoster34 citations
565. Joint Shapley values: a measure of joint feature importancePoster34 citations
566. Should We Be Pre-training? An Argument for End-task Aware Training as an AlternativePoster34 citations
567. Sqrt(d) Dimension Dependence of Langevin Monte CarloPoster34 citations
568. Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive LearningPoster34 citations
569. Variational Neural Cellular AutomataPoster34 citations
570. Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information GamePoster33 citations
571. Conditional Contrastive Learning with KernelPoster33 citations
572. Explanations of Black-Box Models based on Directional Feature InteractionsSpotlight33 citations
573. Focus on the Common Good: Group Distributional Robustness FollowsPoster33 citations
574. Imitation Learning by Reinforcement LearningPoster33 citations
575. Information Prioritization through Empowerment in Visual Model-based RLPoster33 citations
576. Missingness Bias in Model DebuggingPoster33 citations
577. Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time DataPoster33 citations
578. Online Facility Location with PredictionsPoster33 citations
579. PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction LearningPoster33 citations
580. Query Embedding on Hyper-Relational Knowledge GraphsPoster33 citations
581. Sound and Complete Neural Network Repair with Minimality and Locality GuaranteesPoster33 citations
582. Steerable Partial Differential Operators for Equivariant Neural NetworksPoster33 citations
583. Towards Deepening Graph Neural Networks: A GNTK-based Optimization PerspectivePoster33 citations
584. Towards Training Billion Parameter Graph Neural Networks for Atomic SimulationsPoster33 citations
585. Training invariances and the low-rank phenomenon: beyond linear networksPoster33 citations
586. Value Gradient weighted Model-Based Reinforcement LearningSpotlight33 citations
587. How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysisPoster32 citations
588. Monotonic Differentiable Sorting NetworksPoster32 citations
589. Multi-Agent MDP Homomorphic NetworksPoster32 citations
590. Multi-Critic Actor Learning: Teaching RL Policies to Act with StylePoster32 citations
591. On the Optimal Memorization Power of ReLU Neural NetworksSpotlight32 citations
592. Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization MethodsPoster32 citations
593. Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure SpacePoster31 citations
594. AdaAug: Learning Class- and Instance-adaptive Data Augmentation PoliciesPoster31 citations
595. Bag of Instances Aggregation Boosts Self-supervised DistillationPoster31 citations
596. Counterfactual Plans under Distributional AmbiguityPoster31 citations
597. Cross-Trajectory Representation Learning for Zero-Shot Generalization in RLPoster31 citations
598. MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMCPoster31 citations
599. Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPsPoster31 citations
600. Provably Filtering Exogenous Distractors using Multistep Inverse DynamicsOral31 citations
601. Towards Building A Group-based Unsupervised Representation Disentanglement FrameworkPoster31 citations
602. Towards Empirical Sandwich Bounds on the Rate-Distortion FunctionPoster31 citations
603. Understanding the Variance Collapse of SVGD in High DimensionsPoster31 citations
604. Weighted Training for Cross-Task LearningOral31 citations
605. iLQR-VAE : control-based learning of input-driven dynamics with applications to neural dataOral31 citations
606. Learning Curves for SGD on Structured FeaturesPoster30 citations
607. Lossless Compression with Probabilistic CircuitsSpotlight30 citations
608. Multi-objective Optimization by Learning Space PartitionPoster30 citations
609. On Lottery Tickets and Minimal Task Representations in Deep Reinforcement LearningSpotlight30 citations
610. Optimizing Neural Networks with Gradient Lexicase SelectionPoster30 citations
611. Practical Conditional Neural Process Via Tractable Dependent PredictionsPoster30 citations
612. Proving the Lottery Ticket Hypothesis for Convolutional Neural NetworksPoster30 citations
613. RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter EstimationOral30 citations
614. Shuffle Private Stochastic Convex OptimizationPoster30 citations
615. Spanning Tree-based Graph Generation for MoleculesSpotlight30 citations
616. WeakM3D: Towards Weakly Supervised Monocular 3D Object DetectionPoster30 citations
617. $\beta$-Intact-VAE: Identifying and Estimating Causal Effects under Limited OverlapPoster29 citations
618. Active Hierarchical Exploration with Stable Subgoal Representation LearningPoster29 citations
619. Bregman Gradient Policy OptimizationPoster29 citations
620. Fooling Explanations in Text ClassifiersPoster29 citations
621. Interpretable Unsupervised Diversity Denoising and Artefact RemovalSpotlight29 citations
622. Knowledge Infused DecodingPoster29 citations
623. Learning Multimodal VAEs through Mutual SupervisionSpotlight29 citations
624. On Redundancy and Diversity in Cell-based Neural Architecture SearchPoster29 citations
625. On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and ImplicationsPoster29 citations
626. Online Ad Hoc Teamwork under Partial ObservabilityPoster29 citations
627. P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse PromptsPoster29 citations
628. Path Auxiliary Proposal for MCMC in Discrete SpaceSpotlight29 citations
629. QUERY EFFICIENT DECISION BASED SPARSE ATTACKS AGAINST BLACK-BOX DEEP LEARNING MODELSPoster29 citations
630. Stiffness-aware neural network for learning Hamiltonian systemsPoster29 citations
631. Autonomous Learning of Object-Centric Abstractions for High-Level PlanningPoster28 citations
632. Deep Point Cloud ReconstructionPoster28 citations
633. Feature Kernel DistillationPoster28 citations
634. Is Importance Weighting Incompatible with Interpolating Classifiers?Poster28 citations
635. Mapping conditional distributions for domain adaptation under generalized target shiftPoster28 citations
636. On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement LearningPoster28 citations
637. Overcoming The Spectral Bias of Neural Value ApproximationPoster28 citations
638. POETREE: Interpretable Policy Learning with Adaptive Decision TreesSpotlight28 citations
639. Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNsPoster28 citations
640. Self-Supervision Enhanced Feature Selection with Correlated GatesSpotlight28 citations
641. Unifying Likelihood-free Inference with Black-box Optimization and BeyondSpotlight28 citations
642. A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement LearningPoster27 citations
643. A generalization of the randomized singular value decompositionPoster27 citations
644. Compositional Attention: Disentangling Search and RetrievalSpotlight27 citations
645. D-CODE: Discovering Closed-form ODEs from Observed TrajectoriesSpotlight27 citations
646. Efficient and Differentiable Conformal Prediction with General Function ClassesPoster27 citations
647. GeneDisco: A Benchmark for Experimental Design in Drug DiscoveryPoster27 citations
648. How many degrees of freedom do we need to train deep networks: a loss landscape perspectivePoster27 citations
649. Is High Variance Unavoidable in RL? A Case Study in Continuous ControlPoster27 citations
650. Offline Neural Contextual Bandits: Pessimism, Optimization and GeneralizationPoster27 citations
651. On Distributed Adaptive Optimization with Gradient CompressionPoster27 citations
652. Plant 'n' Seek: Can You Find the Winning Ticket?Poster27 citations
653. Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?Poster27 citations
654. SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-TrainingPoster27 citations
655. Towards Deployment-Efficient Reinforcement Learning: Lower Bound and OptimalitySpotlight27 citations
656. Tracking the risk of a deployed model and detecting harmful distribution shiftsPoster27 citations
657. When, Why, and Which Pretrained GANs Are Useful?Poster27 citations
658. A Zest of LIME: Towards Architecture-Independent Model DistancesPoster26 citations
659. Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial PerturbationsPoster26 citations
660. Better Supervisory Signals by Observing Learning PathsPoster26 citations
661. Certified Robustness for Deep Equilibrium Models via Interval Bound PropagationPoster26 citations
662. ClimateGAN: Raising Climate Change Awareness by Generating Images of FloodsPoster26 citations
663. Contact Points Discovery for Soft-Body Manipulations with Differentiable PhysicsSpotlight26 citations
664. Continuous-Time Meta-Learning with Forward Mode DifferentiationSpotlight26 citations
665. Dynamics-Aware Comparison of Learned Reward FunctionsSpotlight26 citations
666. Explaining Point Processes by Learning Interpretable Temporal Logic RulesPoster26 citations
667. Exploring extreme parameter compression for pre-trained language modelsPoster26 citations
668. Generalisation in Lifelong Reinforcement Learning through Logical CompositionPoster26 citations
669. Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time SeriesPoster26 citations
670. L0-Sparse Canonical Correlation AnalysisPoster26 citations
671. LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent LearningPoster26 citations
672. Learning Prototype-oriented Set Representations for Meta-LearningPoster26 citations
673. Model-augmented Prioritized Experience ReplayPoster26 citations
674. Multi-Stage Episodic Control for Strategic Exploration in Text GamesSpotlight26 citations
675. Optimal Transport for Long-Tailed Recognition with Learnable Cost MatrixPoster26 citations
676. Prototype memory and attention mechanisms for few shot image generationPoster26 citations
677. Rethinking Class-Prior Estimation for Positive-Unlabeled LearningPoster26 citations
678. Reverse Engineering of Imperceptible Adversarial Image PerturbationsPoster26 citations
679. Sampling with Mirrored Stein OperatorsSpotlight26 citations
680. Towards Understanding the Data Dependency of Mixup-style TrainingSpotlight26 citations
681. A General Analysis of Example-Selection for Stochastic Gradient DescentSpotlight25 citations
682. Churn Reduction via DistillationSpotlight25 citations
683. Controlling Directions Orthogonal to a ClassifierSpotlight25 citations
684. Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal ReachingPoster25 citations
685. Distributionally Robust Models with Parametric Likelihood RatiosPoster25 citations
686. Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order InformationPoster25 citations
687. Evaluating Distributional Distortion in Neural Language ModelingPoster25 citations
688. Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form SolutionsPoster25 citations
689. Hierarchical Variational Memory for Few-shot Learning Across DomainsPoster25 citations
690. Information Gain Propagation: a New Way to Graph Active Learning with Soft LabelsPoster25 citations
691. MAML is a Noisy Contrastive Learner in ClassificationPoster25 citations
692. RelViT: Concept-guided Vision Transformer for Visual Relational ReasoningPoster25 citations
693. Adaptive Wavelet Transformer Network for 3D Shape Representation LearningPoster24 citations
694. Augmented Sliced Wasserstein DistancesPoster24 citations
695. Contextualized Scene Imagination for Generative Commonsense ReasoningPoster24 citations
696. Energy-Inspired Molecular Conformation OptimizationPoster24 citations
697. Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement LearningPoster24 citations
698. FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual RelationsPoster24 citations
699. FairCal: Fairness Calibration for Face VerificationPoster24 citations
700. Hybrid Random FeaturesPoster24 citations
701. IntSGD: Adaptive Floatless Compression of Stochastic GradientsSpotlight24 citations
702. Learning meta-features for AutoMLSpotlight24 citations
703. Linking Emergent and Natural Languages via Corpus TransferSpotlight24 citations
704. Meta-Imitation Learning by Watching Video DemonstrationsPoster24 citations
705. Model-Based Offline Meta-Reinforcement Learning with RegularizationPoster24 citations
706. NeuPL: Neural Population LearningPoster24 citations
707. On Robust Prefix-Tuning for Text ClassificationPoster24 citations
708. The Three Stages of Learning Dynamics in High-dimensional Kernel MethodsPoster24 citations
709. Unsupervised Vision-Language Grammar Induction with Shared Structure ModelingOral24 citations
710. Approximation and Learning with Deep Convolutional Models: a Kernel PerspectivePoster23 citations
711. Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene DeblurringPoster23 citations
712. It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum GenerationPoster23 citations
713. Label Encoding for Regression NetworksSpotlight23 citations
714. Learning curves for continual learning in neural networks: Self-knowledge transfer and forgettingPoster23 citations
715. Nonlinear ICA Using Volume-Preserving TransformationsPoster23 citations
716. Pareto Policy Pool for Model-based Offline Reinforcement LearningPoster23 citations
717. ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse KinematicsOral23 citations
718. The Close Relationship Between Contrastive Learning and Meta-LearningPoster23 citations
719. Transfer RL across Observation Feature Spaces via Model-Based RegularizationPoster23 citations
720. A global convergence theory for deep ReLU implicit networks via over-parameterizationPoster22 citations
721. Analyzing and Improving the Optimization Landscape of Noise-Contrastive EstimationSpotlight22 citations
722. Autoregressive Quantile Flows for Predictive Uncertainty EstimationSpotlight22 citations
723. C-Planning: An Automatic Curriculum for Learning Goal-Reaching TasksPoster22 citations
724. CoMPS: Continual Meta Policy SearchPoster22 citations
725. Constructing Orthogonal Convolutions in an Explicit MannerPoster22 citations
726. Curriculum learning as a tool to uncover learning principles in the brainPoster22 citations
727. Deep ReLU Networks Preserve Expected LengthPoster22 citations
728. Distribution Compression in Near-Linear TimePoster22 citations
729. Neural Parameter Allocation SearchPoster22 citations
730. On the relation between statistical learning and perceptual distancesSpotlight22 citations
731. Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot ClassificationPoster22 citations
732. Towards Evaluating the Robustness of Neural Networks Learned by TransductionPoster22 citations
733. Anytime Dense Prediction with Confidence AdaptivityPoster21 citations
734. Discrepancy-Based Active Learning for Domain AdaptationPoster21 citations
735. Distributional Reinforcement Learning with Monotonic SplinesPoster21 citations
736. Do Users Benefit From Interpretable Vision? A User Study, Baseline, And DatasetPoster21 citations
737. Finding Biological Plausibility for Adversarially Robust Features via Metameric TasksSpotlight21 citations
738. HyperDQN: A Randomized Exploration Method for Deep Reinforcement LearningPoster21 citations
739. Multiset-Equivariant Set Prediction with Approximate Implicit DifferentiationPoster21 citations
740. Neural Structured Prediction for Inductive Node ClassificationOral21 citations
741. On the Convergence of mSGD and AdaGrad for Stochastic OptimizationPoster21 citations
742. Permutation-Based SGD: Is Random Optimal?Poster21 citations
743. Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov GamePoster21 citations
744. Spike-inspired rank coding for fast and accurate recurrent neural networksSpotlight21 citations
745. The Spectral Bias of Polynomial Neural NetworksPoster21 citations
746. Topological Experience ReplayPoster21 citations
747. Constructing a Good Behavior Basis for Transfer using Generalized Policy UpdatesPoster20 citations
748. Convergent Graph SolversPoster20 citations
749. Hindsight is 20/20: Leveraging Past Traversals to Aid 3D PerceptionPoster20 citations
750. In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal SpecificationsPoster20 citations
751. Know Thyself: Transferable Visual Control Policies Through Robot-AwarenessPoster20 citations
752. Learning to Schedule Learning rate with Graph Neural NetworksPoster20 citations
753. Local Feature Swapping for Generalization in Reinforcement LearningPoster20 citations
754. Neural Processes with Stochastic Attention: Paying more attention to the context datasetPoster20 citations
755. Neural Stochastic Dual Dynamic ProgrammingPoster20 citations
756. Non-Linear Operator Approximations for Initial Value ProblemsPoster20 citations
757. On feature learning in neural networks with global convergence guaranteesPoster20 citations
758. Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint LocalizationPoster20 citations
759. Symbolic Learning to Optimize: Towards Interpretability and ScalabilityPoster20 citations
760. VAE Approximation Error: ELBO and Exponential FamiliesSpotlight20 citations
761. Creating Training Sets via Weak Indirect SupervisionPoster19 citations
762. Dealing with Non-Stationarity in MARL via Trust-Region DecompositionPoster19 citations
763. Demystifying Limited Adversarial Transferability in Automatic Speech Recognition SystemsPoster19 citations
764. Eliminating Sharp Minima from SGD with Truncated Heavy-tailed NoisePoster19 citations
765. Fast Differentiable Matrix Square RootPoster19 citations
766. How Did the Model Change? Efficiently Assessing Machine Learning API ShiftsPoster19 citations
767. Information Bottleneck: Exact Analysis of (Quantized) Neural NetworksPoster19 citations
768. Learning a subspace of policies for online adaptation in Reinforcement LearningPoster19 citations
769. Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in SolverSpotlight19 citations
770. Neural Spectral Marked Point ProcessesPoster19 citations
771. On Covariate Shift of Latent Confounders in Imitation and Reinforcement LearningPoster19 citations
772. Optimal Transport for Causal DiscoverySpotlight19 citations
773. PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural NetworksPoster19 citations
774. Pretraining Text Encoders with Adversarial Mixture of Training Signal GeneratorsPoster19 citations
775. Space-Time Graph Neural NetworksPoster19 citations
776. Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulationPoster19 citations
777. Actor-critic is implicitly biased towards high entropy optimal policiesPoster18 citations
778. Asymmetry Learning for Counterfactually-invariant Classification in OOD TasksOral18 citations
779. Coherence-based Label Propagation over Time Series for Accelerated Active LearningPoster18 citations
780. Distributionally Robust Fair Principal Components via Geodesic DescentsPoster18 citations
781. Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine LearningPoster18 citations
782. Granger causal inference on DAGs identifies genomic loci regulating transcriptionPoster18 citations
783. Learning Versatile Neural Architectures by Propagating Network CodesPoster18 citations
784. Learning Weakly-supervised Contrastive RepresentationsPoster18 citations
785. Pareto Policy AdaptationPoster18 citations
786. SketchODE: Learning neural sketch representation in continuous timePoster18 citations
787. Sparse Attention with Learning to HashPoster18 citations
788. Target-Side Input Augmentation for Sequence to Sequence GenerationPoster18 citations
789. Understanding and Leveraging Overparameterization in Recursive Value EstimationPoster18 citations
790. Understanding approximate and unrolled dictionary learning for pattern recoveryPoster18 citations
791. Anisotropic Random Feature Regression in High DimensionsPoster17 citations
792. CodeTrek: Flexible Modeling of Code using an Extensible Relational RepresentationPoster17 citations
793. Communication-Efficient Actor-Critic Methods for Homogeneous Markov GamesPoster17 citations
794. Disentanglement Analysis with Partial Information DecompositionPoster17 citations
795. Evaluating Model-Based Planning and Planner Amortization for Continuous ControlPoster17 citations
796. Generative Principal Component AnalysisPoster17 citations
797. Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric LearningPoster17 citations
798. Know Your Action Set: Learning Action Relations for Reinforcement LearningPoster17 citations
799. Learning Curves for Gaussian Process Regression with Power-Law Priors and TargetsPoster17 citations
800. Learning Scenario Representation for Solving Two-stage Stochastic Integer ProgramsPoster17 citations
801. On Non-Random Missing Labels in Semi-Supervised LearningPoster17 citations
802. Visual Correspondence HallucinationPoster17 citations
803. A First-Occupancy Representation for Reinforcement LearningPoster16 citations
804. An Operator Theoretic View On Pruning Deep Neural NetworksPoster16 citations
805. Capturing Structural Locality in Non-parametric Language ModelsPoster16 citations
806. Closed-form Sample Probing for Learning Generative Models in Zero-shot LearningPoster16 citations
807. Contrastive Fine-grained Class Clustering via Generative Adversarial NetworksSpotlight16 citations
808. CoordX: Accelerating Implicit Neural Representation with a Split MLP ArchitecturePoster16 citations
809. Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node featuresSpotlight16 citations
810. Domain Adversarial Training: A Game PerspectivePoster16 citations
811. Fast Regression for Structured InputsPoster16 citations
812. Group-based Interleaved Pipeline Parallelism for Large-scale DNN TrainingPoster16 citations
813. Implicit Bias of MSE Gradient Optimization in Underparameterized Neural NetworksPoster16 citations
814. Improving Mutual Information Estimation with Annealed and Energy-Based BoundsPoster16 citations
815. Maximizing Ensemble Diversity in Deep Reinforcement LearningPoster16 citations
816. No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer ModelsPoster16 citations
817. On the Importance of Firth Bias Reduction in Few-Shot ClassificationSpotlight16 citations
818. Relational Multi-Task Learning: Modeling Relations between Data and TasksSpotlight16 citations
819. Sequential Reptile: Inter-Task Gradient Alignment for Multilingual LearningPoster16 citations
820. T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal AnalysisPoster16 citations
821. Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic SpacePoster15 citations
822. Dive Deeper Into Integral Pose RegressionPoster15 citations
823. Do deep networks transfer invariances across classes?Poster15 citations
824. Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and UnpredictabilityPoster15 citations
825. FedChain: Chained Algorithms for Near-optimal Communication Cost in Federated LearningPoster15 citations
826. Fine-grained Differentiable Physics: A Yarn-level Model for FabricsPoster15 citations
827. LOSSY COMPRESSION WITH DISTRIBUTION SHIFT AS ENTROPY CONSTRAINED OPTIMAL TRANSPORTPoster15 citations
828. Learning Hierarchical Structures with Differentiable Nondeterministic StacksSpotlight15 citations
829. Learning Neural Contextual Bandits through Perturbed RewardsPoster15 citations
830. Learning Towards The Largest MarginsPoster15 citations
831. Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimizationPoster15 citations
832. Retriever: Learning Content-Style Representation as a Token-Level Bipartite GraphPoster15 citations
833. Task Affinity with Maximum Bipartite Matching in Few-Shot LearningPoster15 citations
834. Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence ClassificationPoster15 citations
835. The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPsPoster15 citations
836. What Makes Better Augmentation Strategies? Augment Difficult but Not too DifferentPoster15 citations
837. Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral StreamSpotlight15 citations
838. Adversarial Support AlignmentSpotlight14 citations
839. Constraining Linear-chain CRFs to Regular LanguagesPoster14 citations
840. Controlling the Complexity and Lipschitz Constant improves Polynomial NetsPoster14 citations
841. Delaunay Component Analysis for Evaluation of Data RepresentationsPoster14 citations
842. Divisive Feature Normalization Improves Image Recognition Performance in AlexNetPoster14 citations
843. Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian SpectrumsPoster14 citations
844. Fast AdvPropPoster14 citations
845. Generalization Through the Lens of Leave-One-Out ErrorPoster14 citations
846. Goal-Directed Planning via Hindsight Experience ReplayPoster14 citations
847. Gradient Information Matters in Policy Optimization by Back-propagating through ModelPoster14 citations
848. IGLU: Efficient GCN Training via Lazy UpdatesPoster14 citations
849. Imitation Learning from Observations under Transition Model DisparityPoster14 citations
850. Interacting Contour Stochastic Gradient Langevin DynamicsPoster14 citations
851. Non-Parallel Text Style Transfer with Self-Parallel SupervisionPoster14 citations
852. On Predicting Generalization using GANsSpotlight14 citations
853. On the benefits of maximum likelihood estimation for Regression and ForecastingPoster14 citations
854. One After Another: Learning Incremental Skills for a Changing WorldPoster14 citations
855. Online Adversarial AttacksPoster14 citations
856. PoNet: Pooling Network for Efficient Token Mixing in Long SequencesPoster14 citations
857. Policy Gradients Incorporating the FuturePoster14 citations
858. Real-Time Neural Voice CamouflageOral14 citations
859. Shallow and Deep Networks are Near-Optimal Approximators of Korobov FunctionsPoster14 citations
860. Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug DiscoveryPoster14 citations
861. Task Relatedness-Based Generalization Bounds for Meta LearningSpotlight14 citations
862. Task-Induced Representation LearningPoster14 citations
863. The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex ProgramPoster14 citations
864. A Fine-Tuning Approach to Belief State ModelingPoster13 citations
865. A NON-PARAMETRIC REGRESSION VIEWPOINT : GENERALIZATION OF OVERPARAMETRIZED DEEP RELU NETWORK UNDER NOISY OBSERVATIONSPoster13 citations
866. A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial TrainingPoster13 citations
867. Anti-Concentrated Confidence Bonuses For Scalable ExplorationPoster13 citations
868. Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in FuturePoster13 citations
869. Conditioning Sequence-to-sequence Networks with Learned ActivationsPoster13 citations
870. Connectome-constrained Latent Variable Model of Whole-Brain Neural ActivityPoster13 citations
871. Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel SpaceOral13 citations
872. GDA-AM: ON THE EFFECTIVENESS OF SOLVING MIN-IMAX OPTIMIZATION VIA ANDERSON MIXINGPoster13 citations
873. Half-Inverse Gradients for Physical Deep LearningSpotlight13 citations
874. Minimax Optimization with Smooth Algorithmic AdversariesPoster13 citations
875. Model Agnostic Interpretability for Multiple Instance LearningPoster13 citations
876. Normalization of Language Embeddings for Cross-Lingual AlignmentPoster13 citations
877. Phenomenology of Double Descent in Finite-Width Neural NetworksPoster13 citations
878. Provably Robust Adversarial ExamplesPoster13 citations
879. R5: Rule Discovery with Reinforced and Recurrent Relational ReasoningSpotlight13 citations
880. Reinforcement Learning in Presence of Discrete Markovian Context EvolutionPoster13 citations
881. Safe Neurosymbolic Learning with Differentiable Symbolic ExecutionPoster13 citations
882. Signing the Supermask: Keep, Hide, InvertPoster13 citations
883. Superclass-Conditional Gaussian Mixture Model For Learning Fine-Grained EmbeddingsSpotlight13 citations
884. The Role of Pretrained Representations for the OOD Generalization of RL AgentsPoster13 citations
885. Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis QuantizationPoster13 citations
886. Training Structured Neural Networks Through Manifold Identification and Variance ReductionPoster13 citations
887. Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive SymptomsPoster13 citations
888. Variational autoencoders in the presence of low-dimensional data: landscape and implicit biasPoster13 citations
889. switch-GLAT: Multilingual Parallel Machine Translation Via Code-Switch DecoderPoster13 citations
890. A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of DiseasePoster12 citations
891. Concurrent Adversarial Learning for Large-Batch TrainingPoster12 citations
892. Differentiable Expectation-Maximization for Set Representation LearningPoster12 citations
893. Dynamic Token Normalization improves Vision TransformersPoster12 citations
894. EigenGame Unloaded: When playing games is better than optimizingPoster12 citations
895. Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image RetrievalPoster12 citations
896. Learning Continuous Environment Fields via Implicit FunctionsPoster12 citations
897. Learning State Representations via Retracing in Reinforcement LearningPoster12 citations
898. Learning Value Functions from Undirected State-only ExperiencePoster12 citations
899. On the Learning and Learnability of QuasimetricsPoster12 citations
900. Optimization inspired Multi-Branch Equilibrium ModelsPoster12 citations
901. PF-GNN: Differentiable particle filtering based approximation of universal graph representationsPoster12 citations
902. Phase Collapse in Neural NetworksPoster12 citations
903. Provably convergent quasistatic dynamics for mean-field two-player zero-sum gamesPoster12 citations
904. Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and TheorySpotlight12 citations
905. Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space.Poster12 citations
906. Variational Predictive Routing with Nested Subjective TimescalesPoster12 citations
907. Why Propagate Alone? Parallel Use of Labels and Features on GraphsPoster12 citations
908. A Johnson-Lindenstrauss Framework for Randomly Initialized CNNsPoster11 citations
909. A fast and accurate splitting method for optimal transport: analysis and implementationPoster11 citations
910. Case-based reasoning for better generalization in textual reinforcement learningPoster11 citations
911. Constrained Physical-Statistics Models for Dynamical System Identification and PredictionPoster11 citations
912. Gradient Importance Learning for Incomplete ObservationsPoster11 citations
913. Hidden Parameter Recurrent State Space Models For Changing Dynamics ScenariosPoster11 citations
914. Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothnessSpotlight11 citations
915. Learning Altruistic Behaviours in Reinforcement Learning without External RewardsSpotlight11 citations
916. Map Induction: Compositional spatial submap learning for efficient exploration in novel environmentsPoster11 citations
917. Maximum n-times Coverage for Vaccine DesignPoster11 citations
918. Measuring the Interpretability of Unsupervised Representations via Quantized Reversed ProbingPoster11 citations
919. Multi-Task ProcessesPoster11 citations
920. Multimeasurement Generative ModelsPoster11 citations
921. Quantitative Performance Assessment of CNN Units via Topological Entropy CalculationPoster11 citations
922. Random matrices in service of ML footprint: ternary random features with no performance lossPoster11 citations
923. Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit DifferentiationSpotlight11 citations
924. Visual Representation Learning over Latent DomainsPoster11 citations
925. Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and TransformerPoster10 citations
926. Boosted Curriculum Reinforcement LearningPoster10 citations
927. DictFormer: Tiny Transformer with Shared DictionaryPoster10 citations
928. Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn FeaturesPoster10 citations
929. Generalized rectifier wavelet covariance models for texture synthesisPoster10 citations
930. Generative Planning for Temporally Coordinated Exploration in Reinforcement LearningSpotlight10 citations
931. High Probability Generalization Bounds with Fast Rates for Minimax ProblemsPoster10 citations
932. Hindsight Foresight Relabeling for Meta-Reinforcement LearningPoster10 citations
933. Language-biased image classification: evaluation based on semantic representationsPoster10 citations
934. Neural Network Approximation based on Hausdorff distance of Tropical ZonotopesPoster10 citations
935. On Incorporating Inductive Biases into VAEsPoster10 citations
936. On the Convergence of Certified Robust Training with Interval Bound PropagationPoster10 citations
937. On-Policy Model Errors in Reinforcement LearningPoster10 citations
938. Topologically Regularized Data EmbeddingsPoster10 citations
939. Towards Understanding the Robustness Against Evasion Attack on Categorical DataPoster10 citations
940. Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning RatePoster10 citations
941. Variational oracle guiding for reinforcement learningPoster10 citations
942. W-CTC: a Connectionist Temporal Classification Loss with Wild CardsPoster10 citations
943. A Neural Tangent Kernel Perspective of Infinite Tree EnsemblesPoster9 citations
944. Axiomatic Explanations for Visual Search, Retrieval, and Similarity LearningPoster9 citations
945. DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG SignalsPoster9 citations
946. Evidential Turing ProcessesPoster9 citations
947. Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language ModelingSpotlight9 citations
948. Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANsPoster9 citations
949. Huber Additive Models for Non-stationary Time Series AnalysisPoster9 citations
950. Implicit Bias of Adversarial Training for Deep Neural NetworksPoster9 citations
951. Improving the Accuracy of Learning Example Weights for Imbalance ClassificationPoster9 citations
952. Learning Causal Models from Conditional Moment Restrictions by Importance WeightingSpotlight9 citations
953. Learning Features with Parameter-Free LayersPoster9 citations
954. Learning Object-Oriented Dynamics for Planning from TextPoster9 citations
955. Online Hyperparameter Meta-Learning with Hypergradient DistillationSpotlight9 citations
956. PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning MethodPoster9 citations
957. Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It EfficientlyPoster9 citations
958. Prototypical Contrastive Predictive CodingPoster9 citations
959. Relational Surrogate Loss LearningPoster9 citations
960. Scale Mixtures of Neural Network Gaussian ProcessesPoster9 citations
961. The Uncanny Similarity of Recurrence and DepthPoster9 citations
962. A Class of Short-term Recurrence Anderson Mixing Methods and Their ApplicationsPoster8 citations
963. Bi-linear Value Networks for Multi-goal Reinforcement LearningPoster8 citations
964. Causal Contextual Bandits with Targeted InterventionsPoster8 citations
965. Environment Predictive Coding for Visual NavigationPoster8 citations
966. Few-shot Learning via Dirichlet Tessellation EnsemblePoster8 citations
967. Graphon based Clustering and Testing of Networks: Algorithms and TheoryPoster8 citations
968. Inverse Online Learning: Understanding Non-Stationary and Reactionary PoliciesPoster8 citations
969. Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANsPoster8 citations
970. MoReL: Multi-omics Relational LearningPoster8 citations
971. On the Uncomputability of Partition Functions in Energy-Based Sequence ModelsSpotlight8 citations
972. Orchestrated Value Mapping for Reinforcement LearningPoster8 citations
973. Parallel Training of GRU Networks with a Multi-Grid Solver for Long SequencesPoster8 citations
974. Representation-Agnostic Shape FieldsPoster8 citations
975. Towards Understanding Generalization via Decomposing Excess Risk DynamicsPoster8 citations
976. Unrolling PALM for Sparse Semi-Blind Source SeparationPoster8 citations
977. Visual hyperacuity with moving sensor and recurrent neural computationsPoster8 citations
978. A Reduction-Based Framework for Conservative Bandits and Reinforcement LearningPoster7 citations
979. AlphaZero-based Proof Cost Network to Aid Game SolvingPoster7 citations
980. Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one MapsPoster7 citations
981. Convergent and Efficient Deep Q Learning AlgorithmPoster7 citations
982. DIVA: Dataset Derivative of a Learning TaskPoster7 citations
983. Declarative nets that are equilibrium modelsPoster7 citations
984. Fast topological clustering with Wasserstein distancePoster7 citations
985. How Low Can We Go: Trading Memory for Error in Low-Precision TrainingPoster7 citations
986. IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor ScenesPoster7 citations
987. Inductive Relation Prediction Using Analogy Subgraph EmbeddingsPoster7 citations
988. LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODELPoster7 citations
989. Learnability Lock: Authorized Learnability Control Through Adversarial Invertible TransformationsPoster7 citations
990. Learning Discrete Structured Variational Auto-Encoder using Natural Evolution StrategiesPoster7 citations
991. Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral SimilaritiesPoster7 citations
992. Learning to Annotate Part Segmentation with Gradient MatchingPoster7 citations
993. Neural Relational Inference with Node-Specific InformationPoster7 citations
994. On the approximation properties of recurrent encoder-decoder architecturesSpotlight7 citations
995. R4D: Utilizing Reference Objects for Long-Range Distance EstimationPoster7 citations
996. Sparse Communication via Mixed DistributionsOral7 citations
997. Training Transition Policies via Distribution Matching for Complex TasksPoster7 citations
998. Auto-Transfer: Learning to Route Transferable RepresentationsPoster6 citations
999. Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised TranslationPoster6 citations
1000. CrowdPlay: Crowdsourcing Human Demonstrations for Offline LearningPoster6 citations

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