ICLR 2021 Accepted Papers

The full list of 860 papers accepted at ICLR 2021 (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. An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleOral62,867 citations
2. Denoising Diffusion Implicit ModelsPoster8,188 citations
3. Score-Based Generative Modeling through Stochastic Differential EquationsOral7,224 citations
4. Deformable DETR: Deformable Transformers for End-to-End Object DetectionOral6,958 citations
5. Measuring Massive Multitask Language UnderstandingPoster4,192 citations
6. DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTIONPoster3,296 citations
7. Fourier Neural Operator for Parametric Partial Differential EquationsPoster3,172 citations
8. Rethinking Attention with PerformersOral2,032 citations
9. Adaptive Federated OptimizationPoster1,819 citations
10. FastSpeech 2: Fast and High-Quality End-to-End Text to SpeechPoster1,735 citations
11. Sharpness-aware Minimization for Efficiently Improving GeneralizationSpotlight1,709 citations
12. DiffWave: A Versatile Diffusion Model for Audio SynthesisOral1,632 citations
13. In Search of Lost Domain GeneralizationPoster1,378 citations
14. Tent: Fully Test-Time Adaptation by Entropy MinimizationSpotlight1,373 citations
15. GShard: Scaling Giant Models with Conditional Computation and Automatic ShardingPoster1,282 citations
16. Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalPoster1,280 citations
17. Prototypical Contrastive Learning of Unsupervised RepresentationsPoster1,264 citations
18. GraphCodeBERT: Pre-training Code Representations with Data FlowPoster1,214 citations
19. Learning Mesh-Based Simulation with Graph NetworksSpotlight1,101 citations
20. FedBN: Federated Learning on Non-IID Features via Local Batch NormalizationPoster1,089 citations
21. Mastering Atari with Discrete World ModelsPoster1,065 citations
22. Federated Learning Based on Dynamic RegularizationOral1,035 citations
23. Domain Generalization with MixStylePoster1,006 citations
24. On the Bottleneck of Graph Neural Networks and its Practical ImplicationsPoster974 citations
25. Contrastive Learning with Hard Negative SamplesPoster963 citations
26. Adaptive Universal Generalized PageRank Graph Neural NetworkPoster959 citations
27. Long-tail learning via logit adjustmentSpotlight907 citations
28. WaveGrad: Estimating Gradients for Waveform GenerationPoster894 citations
29. Long Range Arena : A Benchmark for Efficient TransformersPoster797 citations
30. In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised LearningPoster743 citations
31. WaNet - Imperceptible Warping-based Backdoor AttackPoster694 citations
32. HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous ClientsPoster677 citations
33. Hopfield Networks is All You NeedPoster673 citations
34. QPLEX: Duplex Dueling Multi-Agent Q-LearningPoster610 citations
35. Aligning AI With Shared Human ValuesPoster607 citations
36. Dataset Condensation with Gradient MatchingOral599 citations
37. Unbiased Teacher for Semi-Supervised Object DetectionPoster598 citations
38. Autoregressive Entity RetrievalSpotlight596 citations
39. Learning Invariant Representations for Reinforcement Learning without ReconstructionOral569 citations
40. Learning from Protein Structure with Geometric Vector PerceptronsSpotlight569 citations
41. Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningPoster561 citations
42. Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural NetworksPoster554 citations
43. Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from PixelsSpotlight533 citations
44. BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionPoster511 citations
45. Revisiting Few-sample BERT Fine-tuningPoster498 citations
46. Long-tailed Recognition by Routing Diverse Distribution-Aware ExpertsSpotlight489 citations
47. ALFWorld: Aligning Text and Embodied Environments for Interactive LearningPoster466 citations
48. Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradientsOral454 citations
49. Noise or Signal: The Role of Image Backgrounds in Object RecognitionPoster454 citations
50. On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong BaselinesPoster453 citations
51. Free Lunch for Few-shot Learning: Distribution CalibrationOral448 citations
52. SSD: A Unified Framework for Self-Supervised Outlier DetectionPoster420 citations
53. Uncertainty Sets for Image Classifiers using Conformal PredictionSpotlight414 citations
54. How Neural Networks Extrapolate: From Feedforward to Graph Neural NetworksOral413 citations
55. Personalized Federated Learning with First Order Model OptimizationPoster413 citations
56. PseudoSeg: Designing Pseudo Labels for Semantic SegmentationPoster413 citations
57. Simple Spectral Graph ConvolutionPoster411 citations
58. Data-Efficient Reinforcement Learning with Self-Predictive RepresentationsSpotlight410 citations
59. Unsupervised Representation Learning for Time Series with Temporal Neighborhood CodingPoster403 citations
60. Random Feature AttentionSpotlight401 citations
61. Recurrent Independent MechanismsSpotlight389 citations
62. Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on ImagesSpotlight385 citations
63. FedBE: Making Bayesian Model Ensemble Applicable to Federated LearningPoster383 citations
64. Discrete Graph Structure Learning for Forecasting Multiple Time SeriesPoster381 citations
65. Transformer protein language models are unsupervised structure learnersPoster380 citations
66. Combining Label Propagation and Simple Models out-performs Graph Neural NetworksPoster373 citations
67. Zero-Cost Proxies for Lightweight NASPoster372 citations
68. Gradient Projection Memory for Continual LearningOral368 citations
69. BERTology Meets Biology: Interpreting Attention in Protein Language ModelsPoster367 citations
70. The Risks of Invariant Risk MinimizationPoster367 citations
71. What Should Not Be Contrastive in Contrastive LearningPoster361 citations
72. Large Scale Image Completion via Co-Modulated Generative Adversarial NetworksSpotlight354 citations
73. Robust early-learning: Hindering the memorization of noisy labelsPoster354 citations
74. Structured Prediction as Translation between Augmented Natural LanguagesSpotlight352 citations
75. Rethinking Positional Encoding in Language Pre-trainingPoster348 citations
76. Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and DepthPoster342 citations
77. Geometry-aware Instance-reweighted Adversarial TrainingOral339 citations
78. How to Find Your Friendly Neighborhood: Graph Attention Design with Self-SupervisionPoster334 citations
79. Exploring Balanced Feature Spaces for Representation LearningPoster331 citations
80. Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired PerspectivePoster331 citations
81. Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated LearningPoster329 citations
82. Nearest Neighbor Machine TranslationPoster329 citations
83. Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image SynthesisPoster328 citations
84. Inductive Representation Learning in Temporal Networks via Causal Anonymous WalksPoster327 citations
85. Bag of Tricks for Adversarial TrainingPoster326 citations
86. Randomized Ensembled Double Q-Learning: Learning Fast Without a ModelPoster323 citations
87. Interpreting Graph Neural Networks for NLP With Differentiable Edge MaskingSpotlight319 citations
88. How Does Mixup Help With Robustness and Generalization?Spotlight313 citations
89. Gradient Descent on Neural Networks Typically Occurs at the Edge of StabilityPoster311 citations
90. Differentially Private Learning Needs Better Features (or Much More Data)Spotlight310 citations
91. The Intrinsic Dimension of Images and Its Impact on LearningSpotlight310 citations
92. Few-Shot Learning via Learning the Representation, ProvablyPoster305 citations
93. Support-set bottlenecks for video-text representation learningSpotlight302 citations
94. Representation Learning via Invariant Causal MechanismsPoster301 citations
95. Explainable Deep One-Class ClassificationPoster297 citations
96. Learning N:M Fine-grained Structured Sparse Neural Networks From ScratchPoster296 citations
97. Dataset Meta-Learning from Kernel Ridge-RegressionPoster294 citations
98. Training with Quantization Noise for Extreme Model CompressionPoster292 citations
99. Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint LearningPoster286 citations
100. Layer-adaptive Sparsity for the Magnitude-based PruningPoster280 citations
101. Theoretical Analysis of Self-Training with Deep Networks on Unlabeled DataOral278 citations
102. Pruning Neural Networks at Initialization: Why Are We Missing the Mark?Poster275 citations
103. Learning and Evaluating Representations for Deep One-Class ClassificationPoster271 citations
104. Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural NetworksPoster271 citations
105. Distilling Knowledge from Reader to Retriever for Question AnsweringPoster269 citations
106. Witches' Brew: Industrial Scale Data Poisoning via Gradient MatchingPoster269 citations
107. Robust and Generalizable Visual Representation Learning via Random ConvolutionsPoster267 citations
108. Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsPoster262 citations
109. Better Fine-Tuning by Reducing Representational CollapsePoster261 citations
110. RODE: Learning Roles to Decompose Multi-Agent TasksPoster260 citations
111. Learning with Instance-Dependent Label Noise: A Sample Sieve ApproachPoster255 citations
112. Influence Functions in Deep Learning Are FragilePoster254 citations
113. Training independent subnetworks for robust predictionPoster252 citations
114. Accurate Learning of Graph Representations with Graph Multiset PoolingPoster251 citations
115. DC3: A learning method for optimization with hard constraintsPoster251 citations
116. Multi-Time Attention Networks for Irregularly Sampled Time SeriesPoster249 citations
117. Perceptual Adversarial Robustness: Defense Against Unseen Threat ModelsPoster249 citations
118. On the Origin of Implicit Regularization in Stochastic Gradient DescentPoster248 citations
119. Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete VerifiersPoster247 citations
120. SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better RegularizationPoster246 citations
121. AdaSpeech: Adaptive Text to Speech for Custom VoicePoster242 citations
122. RNNLogic: Learning Logic Rules for Reasoning on Knowledge GraphsPoster241 citations
123. End-to-end Adversarial Text-to-SpeechOral239 citations
124. Analyzing the Expressive Power of Graph Neural Networks in a Spectral PerspectivePoster235 citations
125. Self-supervised Learning from a Multi-view PerspectivePoster235 citations
126. Uncertainty Estimation in Autoregressive Structured PredictionPoster235 citations
127. Rethinking Architecture Selection in Differentiable NASOral233 citations
128. SEED: Self-supervised Distillation For Visual RepresentationPoster233 citations
129. Robust Overfitting may be mitigated by properly learned smootheningPoster232 citations
130. Colorization TransformerPoster231 citations
131. Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing FlowsSpotlight231 citations
132. What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale StudyOral230 citations
133. Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge GraphsPoster229 citations
134. FedMix: Approximation of Mixup under Mean Augmented Federated LearningPoster229 citations
135. EVALUATION OF NEURAL ARCHITECTURES TRAINED WITH SQUARE LOSS VS CROSS-ENTROPY IN CLASSIFICATION TASKSPoster227 citations
136. LambdaNetworks: Modeling long-range Interactions without AttentionSpotlight224 citations
137. Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement LearningSpotlight222 citations
138. Understanding the failure modes of out-of-distribution generalizationPoster220 citations
139. Unlearnable Examples: Making Personal Data UnexploitableSpotlight220 citations
140. BOIL: Towards Representation Change for Few-shot LearningPoster219 citations
141. DARTS-: Robustly Stepping out of Performance Collapse Without IndicatorsPoster219 citations
142. Degree-Quant: Quantization-Aware Training for Graph Neural NetworksPoster219 citations
143. NBDT: Neural-Backed Decision TreePoster219 citations
144. You Only Need Adversarial Supervision for Semantic Image SynthesisPoster219 citations
145. Robust Reinforcement Learning on State Observations with Learned Optimal AdversaryPoster218 citations
146. Co-Mixup: Saliency Guided Joint Mixup with Supermodular DiversityOral216 citations
147. Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual ModelsSpotlight215 citations
148. Learning explanations that are hard to varyPoster214 citations
149. Incorporating Symmetry into Deep Dynamics Models for Improved GeneralizationPoster212 citations
150. Learning to Reach Goals via Iterated Supervised LearningOral212 citations
151. A Good Image Generator Is What You Need for High-Resolution Video SynthesisSpotlight211 citations
152. Anatomy of Catastrophic Forgetting: Hidden Representations and Task SemanticsPoster211 citations
153. OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement LearningPoster209 citations
154. Graph Information Bottleneck for Subgraph RecognitionPoster206 citations
155. Open Question Answering over Tables and TextPoster206 citations
156. BREEDS: Benchmarks for Subpopulation ShiftPoster205 citations
157. Large Associative Memory Problem in Neurobiology and Machine LearningPoster205 citations
158. AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant WeightsPoster204 citations
159. Retrieval-Augmented Generation for Code Summarization via Hybrid GNNSpotlight204 citations
160. Neural Pruning via Growing RegularizationPoster202 citations
161. Rethinking Soft Labels for Knowledge Distillation: A Bias–Variance Tradeoff PerspectivePoster202 citations
162. What Makes Instance Discrimination Good for Transfer Learning?Poster201 citations
163. LEAF: A Learnable Frontend for Audio ClassificationPoster200 citations
164. Augmenting Physical Models with Deep Networks for Complex Dynamics ForecastingOral199 citations
165. Is Attention Better Than Matrix Decomposition?Poster199 citations
166. Towards Impartial Multi-task LearningPoster198 citations
167. What are the Statistical Limits of Offline RL with Linear Function Approximation?Spotlight198 citations
168. Learning with Feature-Dependent Label Noise: A Progressive ApproachSpotlight195 citations
169. Knowledge distillation via softmax regression representation learningPoster194 citations
170. Self-Supervised Policy Adaptation during DeploymentSpotlight192 citations
171. Implicit Gradient RegularizationPoster189 citations
172. Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech SynthesisPoster188 citations
173. Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine TranslationPoster187 citations
174. Deep Neural Network Fingerprinting by Conferrable Adversarial ExamplesSpotlight186 citations
175. Optimism in Reinforcement Learning with Generalized Linear Function ApproximationPoster186 citations
176. Expressive Power of Invariant and Equivariant Graph Neural NetworksSpotlight185 citations
177. Deployment-Efficient Reinforcement Learning via Model-Based Offline OptimizationPoster179 citations
178. Fair Mixup: Fairness via InterpolationPoster179 citations
179. FairBatch: Batch Selection for Model FairnessPoster179 citations
180. Hyperbolic Neural Networks++Poster179 citations
181. MARS: Markov Molecular Sampling for Multi-objective Drug DiscoverySpotlight179 citations
182. Multiplicative Filter NetworksPoster179 citations
183. Shapley explainability on the data manifoldPoster177 citations
184. Learning Safe Multi-agent Control with Decentralized Neural Barrier CertificatesPoster175 citations
185. Minimum Width for Universal ApproximationSpotlight171 citations
186. Model-Based Offline PlanningPoster170 citations
187. A Universal Representation Transformer Layer for Few-Shot Image ClassificationPoster169 citations
188. Conservative Safety Critics for ExplorationPoster168 citations
189. Learning with AMIGo: Adversarially Motivated Intrinsic GoalsPoster168 citations
190. Parrot: Data-Driven Behavioral Priors for Reinforcement LearningOral168 citations
191. R-GAP: Recursive Gradient Attack on PrivacyPoster168 citations
192. Deep Partition Aggregation: Provable Defenses against General Poisoning AttacksPoster167 citations
193. The Importance of Pessimism in Fixed-Dataset Policy OptimizationPoster167 citations
194. Tilted Empirical Risk MinimizationPoster167 citations
195. DrNAS: Dirichlet Neural Architecture SearchPoster166 citations
196. SALD: Sign Agnostic Learning with DerivativesPoster165 citations
197. LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial RecognitionPoster163 citations
198. Complex Query Answering with Neural Link PredictorsOral162 citations
199. Learning the Pareto Front with HypernetworksPoster162 citations
200. MultiModalQA: complex question answering over text, tables and imagesPoster162 citations
201. CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer LearningPoster161 citations
202. On Position Embeddings in BERTPoster161 citations
203. A Diffusion Theory For Deep Learning Dynamics: Stochastic Gradient Descent Exponentially Favors Flat MinimaPoster159 citations
204. Dance Revolution: Long-Term Dance Generation with Music via Curriculum LearningPoster159 citations
205. Neural Thompson SamplingPoster159 citations
206. DOP: Off-Policy Multi-Agent Decomposed Policy GradientsPoster158 citations
207. Primal Wasserstein Imitation LearningPoster158 citations
208. Self-training For Few-shot Transfer Across Extreme Task DifferencesOral157 citations
209. Counterfactual Generative NetworksPoster156 citations
210. HW-NAS-Bench: Hardware-Aware Neural Architecture Search BenchmarkSpotlight155 citations
211. Linear Mode Connectivity in Multitask and Continual LearningPoster155 citations
212. PSTNet: Point Spatio-Temporal Convolution on Point Cloud SequencesPoster155 citations
213. Rethinking Embedding Coupling in Pre-trained Language ModelsPoster155 citations
214. Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank LearningPoster155 citations
215. Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse CodingOral154 citations
216. Watch-And-Help: A Challenge for Social Perception and Human-AI CollaborationSpotlight154 citations
217. $i$-Mix: A Domain-Agnostic Strategy for Contrastive Representation LearningPoster153 citations
218. Calibration of Neural Networks using SplinesPoster153 citations
219. Learning Neural Generative Dynamics for Molecular Conformation GenerationPoster153 citations
220. Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNsPoster153 citations
221. How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?Poster152 citations
222. Language-Agnostic Representation Learning of Source Code from Structure and ContextPoster152 citations
223. Optimal Regularization can Mitigate Double DescentPoster152 citations
224. Characterizing signal propagation to close the performance gap in unnormalized ResNetsPoster151 citations
225. Getting a CLUE: A Method for Explaining Uncertainty EstimatesOral151 citations
226. Dataset Inference: Ownership Resolution in Machine LearningSpotlight150 citations
227. Improving Adversarial Robustness via Channel-wise Activation SuppressingSpotlight149 citations
228. Learning Neural Event Functions for Ordinary Differential EquationsPoster148 citations
229. Model Patching: Closing the Subgroup Performance Gap with Data AugmentationPoster148 citations
230. On Dyadic Fairness: Exploring and Mitigating Bias in Graph ConnectionsPoster148 citations
231. When Do Curricula Work?Oral148 citations
232. DeLighT: Deep and Light-weight TransformerPoster147 citations
233. Federated Learning via Posterior Averaging: A New Perspective and Practical AlgorithmsPoster146 citations
234. Generalized Energy Based ModelsPoster145 citations
235. Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural RenderingOral145 citations
236. Learning Energy-Based Models by Diffusion Recovery LikelihoodPoster145 citations
237. Adversarial score matching and improved sampling for image generationPoster144 citations
238. InfoBERT: Improving Robustness of Language Models from An Information Theoretic PerspectivePoster143 citations
239. Linear Last-iterate Convergence in Constrained Saddle-point OptimizationPoster143 citations
240. A Distributional Approach to Controlled Text GenerationOral142 citations
241. Lipschitz Recurrent Neural NetworksPoster142 citations
242. Shape-Texture Debiased Neural Network TrainingPoster142 citations
243. Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphsSpotlight141 citations
244. Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman KernelsPoster140 citations
245. Clustering-friendly Representation Learning via Instance Discrimination and Feature DecorrelationPoster139 citations
246. Contrastive Learning with Adversarial Perturbations for Conditional Text GenerationPoster138 citations
247. Robust Curriculum Learning: from clean label detection to noisy label self-correctionPoster138 citations
248. Orthogonalizing Convolutional Layers with the Cayley TransformSpotlight137 citations
249. VAEBM: A Symbiosis between Variational Autoencoders and Energy-based ModelsSpotlight137 citations
250. Directed Acyclic Graph Neural NetworksPoster136 citations
251. PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable PhysicsSpotlight135 citations
252. Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANsOral133 citations
253. MELR: Meta-Learning via Modeling Episode-Level Relationships for Few-Shot LearningPoster133 citations
254. Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private LearningPoster132 citations
255. Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement LearningPoster132 citations
256. Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?Spotlight131 citations
257. Attentional Constellation Nets for Few-Shot LearningPoster131 citations
258. Systematic generalisation with group invariant predictionsSpotlight131 citations
259. FairFil: Contrastive Neural Debiasing Method for Pretrained Text EncodersPoster130 citations
260. Wasserstein-2 Generative NetworksPoster130 citations
261. Isotropy in the Contextual Embedding Space: Clusters and ManifoldsPoster129 citations
262. Neural Spatio-Temporal Point ProcessesPoster129 citations
263. Online Adversarial Purification based on Self-supervised LearningPoster129 citations
264. Bypassing the Ambient Dimension: Private SGD with Gradient Subspace IdentificationPoster128 citations
265. MoPro: Webly Supervised Learning with Momentum PrototypesPoster127 citations
266. Towards Robustness Against Natural Language Word SubstitutionsSpotlight127 citations
267. Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPUPoster126 citations
268. Communication in Multi-Agent Reinforcement Learning: Intention SharingPoster125 citations
269. Uncertainty in Gradient Boosting via EnsemblesPoster124 citations
270. Active Contrastive Learning of Audio-Visual Video RepresentationsPoster122 citations
271. A PAC-Bayesian Approach to Generalization Bounds for Graph Neural NetworksPoster121 citations
272. Learning to Set Waypoints for Audio-Visual NavigationPoster120 citations
273. Net-DNF: Effective Deep Modeling of Tabular DataPoster119 citations
274. Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependenciesOral118 citations
275. Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHSPoster118 citations
276. Incremental few-shot learning via vector quantization in deep embedded spacePoster118 citations
277. Learning from others' mistakes: Avoiding dataset biases without modeling themPoster118 citations
278. Progressive Skeletonization: Trimming more fat from a network at initializationPoster118 citations
279. The role of Disentanglement in GeneralisationPoster118 citations
280. AdaGCN: Adaboosting Graph Convolutional Networks into Deep ModelsPoster117 citations
281. Generalized Multimodal ELBOPoster115 citations
282. Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted NetworkPoster114 citations
283. VTNet: Visual Transformer Network for Object Goal NavigationPoster114 citations
284. Distributional Sliced-Wasserstein and Applications to Generative ModelingSpotlight113 citations
285. Topology-Aware Segmentation Using Discrete Morse TheorySpotlight112 citations
286. On Statistical Bias In Active Learning: How and When to Fix ItSpotlight111 citations
287. Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight MasksPoster110 citations
288. Benchmarks for Deep Off-Policy EvaluationPoster109 citations
289. IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot LearningPoster109 citations
290. Meta-learning Symmetries by ReparameterizationPoster109 citations
291. Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ ParametersSpotlight108 citations
292. Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein StructuresPoster108 citations
293. Wasserstein Embedding for Graph LearningPoster108 citations
294. Deep Equals Shallow for ReLU Networks in Kernel RegimesPoster107 citations
295. Mind the Pad -- CNNs Can Develop Blind SpotsSpotlight107 citations
296. A Unified Approach to Interpreting and Boosting Adversarial TransferabilityPoster106 citations
297. Dynamic Tensor RematerializationSpotlight106 citations
298. GraPPa: Grammar-Augmented Pre-Training for Table Semantic ParsingPoster106 citations
299. Learning to Recombine and Resample Data For Compositional GeneralizationPoster106 citations
300. MiCE: Mixture of Contrastive Experts for Unsupervised Image ClusteringPoster106 citations
301. Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex OptimizationPoster105 citations
302. Off-Dynamics Reinforcement Learning: Training for Transfer with Domain ClassifiersPoster105 citations
303. Efficient Continual Learning with Modular Networks and Task-Driven PriorsPoster104 citations
304. Empirical or Invariant Risk Minimization? A Sample Complexity PerspectivePoster104 citations
305. Grounding Physical Concepts of Objects and Events Through Dynamic Visual ReasoningPoster104 citations
306. On the Universality of Rotation Equivariant Point Cloud NetworksPoster104 citations
307. Transient Non-stationarity and Generalisation in Deep Reinforcement LearningPoster104 citations
308. Adversarially Guided Actor-CriticPoster103 citations
309. Concept Learners for Few-Shot LearningPoster103 citations
310. Graph Coarsening with Neural NetworksPoster103 citations
311. Behavioral Cloning from Noisy DemonstrationsSpotlight102 citations
312. CcGAN: Continuous Conditional Generative Adversarial Networks for Image GenerationPoster102 citations
313. Negative Data AugmentationPoster102 citations
314. Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical StudyPoster101 citations
315. Revisiting Locally Supervised Learning: an Alternative to End-to-end TrainingPoster101 citations
316. CoCon: A Self-Supervised Approach for Controlled Text GenerationPoster100 citations
317. Understanding and Improving Lexical Choice in Non-Autoregressive TranslationPoster100 citations
318. Conditional Negative Sampling for Contrastive Learning of Visual RepresentationsPoster99 citations
319. Evolving Reinforcement Learning AlgorithmsOral99 citations
320. Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that GeneralizeSpotlight99 citations
321. Text Generation by Learning from DemonstrationsPoster99 citations
322. Adversarially-Trained Deep Nets Transfer Better: Illustration on Image ClassificationPoster98 citations
323. CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language UnderstandingPoster98 citations
324. RMSprop converges with proper hyper-parameterSpotlight98 citations
325. Semantic Re-tuning with Contrastive TensionPoster98 citations
326. A unifying view on implicit bias in training linear neural networksPoster97 citations
327. Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less DataPoster97 citations
328. Interactive Weak Supervision: Learning Useful Heuristics for Data LabelingPoster97 citations
329. Risk-Averse Offline Reinforcement LearningPoster97 citations
330. The Recurrent Neural Tangent KernelPoster97 citations
331. A Mathematical Exploration of Why Language Models Help Solve Downstream TasksPoster95 citations
332. CPR: Classifier-Projection Regularization for Continual LearningPoster95 citations
333. Learnable Embedding sizes for Recommender SystemsPoster95 citations
334. My Body is a Cage: the Role of Morphology in Graph-Based Incompatible ControlPoster95 citations
335. On the Transfer of Disentangled Representations in Realistic SettingsPoster95 citations
336. On the role of planning in model-based deep reinforcement learningPoster95 citations
337. Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive LearningPoster95 citations
338. Parameter Efficient Multimodal Transformers for Video Representation LearningPoster94 citations
339. C-Learning: Learning to Achieve Goals via Recursive ClassificationPoster93 citations
340. Creative Sketch GenerationPoster93 citations
341. Hierarchical Reinforcement Learning by Discovering Intrinsic OptionsPoster93 citations
342. Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based ModelsPoster93 citations
343. Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space NavigationPoster92 citations
344. Heteroskedastic and Imbalanced Deep Learning with Adaptive RegularizationPoster92 citations
345. Coping with Label Shift via Distributionally Robust OptimisationPoster91 citations
346. Dual-mode ASR: Unify and Improve Streaming ASR with Full-context ModelingPoster91 citations
347. Share or Not? Learning to Schedule Language-Specific Capacity for Multilingual TranslationOral91 citations
348. Learning a Latent Search Space for Routing Problems using Variational AutoencodersPoster90 citations
349. MixKD: Towards Efficient Distillation of Large-scale Language ModelsPoster90 citations
350. Revisiting Dynamic Convolution via Matrix DecompositionPoster90 citations
351. Byzantine-Resilient Non-Convex Stochastic Gradient DescentPoster89 citations
352. Geometry-Aware Gradient Algorithms for Neural Architecture SearchSpotlight89 citations
353. Learning perturbation sets for robust machine learningPoster89 citations
354. Shape or Texture: Understanding Discriminative Features in CNNsPoster89 citations
355. Few-Shot Bayesian Optimization with Deep Kernel SurrogatesPoster88 citations
356. MONGOOSE: A Learnable LSH Framework for Efficient Neural Network TrainingOral88 citations
357. not-MIWAE: Deep Generative Modelling with Missing not at Random DataPoster88 citations
358. BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network QuantizationPoster87 citations
359. FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior RegularizationPoster87 citations
360. Interpretable Models for Granger Causality Using Self-explaining Neural NetworksPoster87 citations
361. On Learning Universal Representations Across LanguagesPoster87 citations
362. On the geometry of generalization and memorization in deep neural networksPoster87 citations
363. Boost then Convolve: Gradient Boosting Meets Graph Neural NetworksPoster86 citations
364. Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen SoundsPoster86 citations
365. Learning Accurate Entropy Model with Global Reference for Image CompressionPoster86 citations
366. MODALS: Modality-agnostic Automated Data Augmentation in the Latent SpacePoster86 citations
367. NAS-Bench-ASR: Reproducible Neural Architecture Search for Speech RecognitionPoster86 citations
368. Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning DynamicsPoster86 citations
369. Scalable Bayesian Inverse Reinforcement LearningPoster86 citations
370. Adaptive and Generative Zero-Shot LearningPoster85 citations
371. Grounded Language Learning Fast and SlowSpotlight85 citations
372. Learning continuous-time PDEs from sparse data with graph neural networksPoster85 citations
373. Quantifying Differences in Reward FunctionsSpotlight85 citations
374. Targeted Attack against Deep Neural Networks via Flipping Limited Weight BitsPoster85 citations
375. The Deep Bootstrap Framework: Good Online Learners are Good Offline GeneralizersPoster85 citations
376. Using latent space regression to analyze and leverage compositionality in GANsPoster85 citations
377. Viewmaker Networks: Learning Views for Unsupervised Representation LearningPoster85 citations
378. Enforcing robust control guarantees within neural network policiesPoster84 citations
379. Explaining the Efficacy of Counterfactually Augmented DataPoster84 citations
380. Neural ODE ProcessesPoster84 citations
381. Learning Deep Features in Instrumental Variable RegressionPoster83 citations
382. Long Live the Lottery: The Existence of Winning Tickets in Lifelong LearningPoster83 citations
383. MetaNorm: Learning to Normalize Few-Shot Batches Across DomainsPoster83 citations
384. Training GANs with Stronger Augmentations via Contrastive DiscriminatorPoster83 citations
385. A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network InferenceSpotlight82 citations
386. Empirical Analysis of Unlabeled Entity Problem in Named Entity RecognitionPoster82 citations
387. IsarStep: a Benchmark for High-level Mathematical ReasoningPoster82 citations
388. Symmetry-Aware Actor-Critic for 3D Molecular DesignPoster82 citations
389. Emergent Symbols through Binding in External MemorySpotlight81 citations
390. Grounding Language to Autonomously-Acquired Skills via Goal GenerationPoster81 citations
391. Neural Topic Model via Optimal TransportSpotlight81 citations
392. PMI-Masking: Principled masking of correlated spansSpotlight81 citations
393. Predicting Inductive Biases of Pre-Trained ModelsPoster81 citations
394. CO2: Consistent Contrast for Unsupervised Visual Representation LearningPoster80 citations
395. CaPC Learning: Confidential and Private Collaborative LearningPoster80 citations
396. Generalized Variational Continual LearningPoster80 citations
397. SCoRe: Pre-Training for Context Representation in Conversational Semantic ParsingPoster79 citations
398. Combining Ensembles and Data Augmentation Can Harm Your CalibrationPoster78 citations
399. Neural Approximate Sufficient Statistics for Implicit ModelsSpotlight78 citations
400. AdaFuse: Adaptive Temporal Fusion Network for Efficient Action RecognitionPoster77 citations
401. Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian ProcessesPoster77 citations
402. Cross-Attentional Audio-Visual Fusion for Weakly-Supervised Action LocalizationPoster77 citations
403. VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous TreatmentsOral77 citations
404. A statistical theory of cold posteriors in deep neural networksPoster76 citations
405. CT-Net: Channel Tensorization Network for Video ClassificationPoster76 citations
406. Neural Synthesis of Binaural Speech From Mono AudioOral76 citations
407. Reinforcement Learning with Random DelaysPoster76 citations
408. Improving Zero-Shot Voice Style Transfer via Disentangled Representation LearningPoster75 citations
409. Pre-training Text-to-Text Transformers for Concept-centric Common SensePoster75 citations
410. A Better Alternative to Error Feedback for Communication-Efficient Distributed LearningPoster74 citations
411. EEC: Learning to Encode and Regenerate Images for Continual LearningPoster74 citations
412. How Benign is Benign Overfitting ?Spotlight74 citations
413. Prototypical Representation Learning for Relation ExtractionPoster74 citations
414. Teaching Temporal Logics to Neural NetworksPoster74 citations
415. Answering Complex Open-Domain Questions with Multi-Hop Dense RetrievalPoster73 citations
416. High-Capacity Expert Binary NetworksPoster73 citations
417. Learning Cross-Domain Correspondence for Control with Dynamics Cycle-ConsistencyOral73 citations
418. SAFENet: A Secure, Accurate and Fast Neural Network InferencePoster73 citations
419. CoCo: Controllable Counterfactuals for Evaluating Dialogue State TrackersPoster72 citations
420. Contextual Transformation Networks for Online Continual LearningPoster71 citations
421. DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial EstimationPoster71 citations
422. In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution RobustnessPoster71 citations
423. Scaling the Convex Barrier with Active SetsPoster71 citations
424. SenSeI: Sensitive Set Invariance for Enforcing Individual FairnessOral70 citations
425. Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-CriticSpotlight70 citations
426. Class Normalization for (Continual)? Generalized Zero-Shot LearningPoster69 citations
427. Evaluations and Methods for Explanation through Robustness AnalysisPoster69 citations
428. Growing Efficient Deep Networks by Structured Continuous SparsificationOral69 citations
429. Model-Based Visual Planning with Self-Supervised Functional DistancesSpotlight69 citations
430. A Gradient Flow Framework For Analyzing Network PruningSpotlight68 citations
431. Auxiliary Learning by Implicit DifferentiationPoster68 citations
432. BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided ExplorationSpotlight68 citations
433. Partitioned Learned Bloom FiltersPoster68 citations
434. Distributed Momentum for Byzantine-resilient Stochastic Gradient DescentPoster67 citations
435. Evaluation of Similarity-based ExplanationsPoster67 citations
436. Group Equivariant Stand-Alone Self-Attention For VisionPoster67 citations
437. Learning Long-term Visual Dynamics with Region Proposal Interaction NetworksPoster67 citations
438. MALI: A memory efficient and reverse accurate integrator for Neural ODEsPoster67 citations
439. Scalable Transfer Learning with Expert ModelsPoster67 citations
440. GANs Can Play Lottery Tickets TooPoster66 citations
441. On Graph Neural Networks versus Graph-Augmented MLPsPoster66 citations
442. Variational Information Bottleneck for Effective Low-Resource Fine-TuningPoster66 citations
443. A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to AttentionPoster65 citations
444. A Wigner-Eckart Theorem for Group Equivariant Convolution KernelsPoster65 citations
445. Initialization and Regularization of Factorized Neural LayersPoster65 citations
446. Remembering for the Right Reasons: Explanations Reduce Catastrophic ForgettingPoster65 citations
447. Distance-Based Regularisation of Deep Networks for Fine-TuningPoster64 citations
448. Generative Scene Graph NetworksPoster64 citations
449. When Optimizing $f$-Divergence is Robust with Label NoisePoster64 citations
450. Discovering Diverse Multi-Agent Strategic Behavior via Reward RandomizationPoster63 citations
451. Fully Unsupervised Diversity Denoising with Convolutional Variational AutoencodersPoster63 citations
452. MIROSTAT: A NEURAL TEXT DECODING ALGORITHM THAT DIRECTLY CONTROLS PERPLEXITYPoster63 citations
453. Meta-GMVAE: Mixture of Gaussian VAE for Unsupervised Meta-LearningSpotlight63 citations
454. Refining Deep Generative Models via Discriminator Gradient FlowPoster63 citations
455. Generating Adversarial Computer Programs using Optimized ObfuscationsPoster62 citations
456. Impact of Representation Learning in Linear BanditsPoster62 citations
457. Offline Model-Based Optimization via Normalized Maximum Likelihood EstimationPoster62 citations
458. On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningPoster62 citations
459. Selective Classification Can Magnify Disparities Across GroupsPoster62 citations
460. Tradeoffs in Data Augmentation: An Empirical StudyPoster62 citations
461. Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?Oral62 citations
462. Linear Convergent Decentralized Optimization with CompressionPoster61 citations
463. Probing BERT in Hyperbolic SpacesPoster61 citations
464. Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated EnvironmentsPoster61 citations
465. Representation Balancing Offline Model-based Reinforcement LearningPoster61 citations
466. Robust Pruning at InitializationPoster61 citations
467. Shapley Explanation NetworksPoster61 citations
468. Auction Learning as a Two-Player GamePoster60 citations
469. BiPointNet: Binary Neural Network for Point CloudsPoster60 citations
470. Early Stopping in Deep Networks: Double Descent and How to Eliminate itPoster60 citations
471. Efficient Conformal Prediction via Cascaded Inference with Expanded AdmissionPoster60 citations
472. EigenGame: PCA as a Nash EquilibriumOral60 citations
473. Human-Level Performance in No-Press Diplomacy via Equilibrium SearchOral60 citations
474. Contrastive Syn-to-Real GeneralizationPoster59 citations
475. INT: An Inequality Benchmark for Evaluating Generalization in Theorem ProvingPoster59 citations
476. Mathematical Reasoning via Self-supervised Skip-tree TrainingSpotlight59 citations
477. Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel RegimeOral59 citations
478. Trajectory Prediction using Equivariant Continuous ConvolutionPoster59 citations
479. Adaptive Extra-Gradient Methods for Min-Max Optimization and GamesPoster58 citations
480. Network Pruning That Matters: A Case Study on Retraining VariantsPoster58 citations
481. Neural gradients are near-lognormal: improved quantized and sparse trainingPoster58 citations
482. Return-Based Contrastive Representation Learning for Reinforcement LearningPoster58 citations
483. Sample-Efficient Automated Deep Reinforcement LearningPoster58 citations
484. Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNsPoster58 citations
485. Continuous Wasserstein-2 Barycenter Estimation without Minimax OptimizationPoster57 citations
486. Learning Robust State Abstractions for Hidden-Parameter Block MDPsPoster57 citations
487. Learning Subgoal Representations with Slow DynamicsPoster57 citations
488. Rapid Neural Architecture Search by Learning to Generate Graphs from DatasetsPoster57 citations
489. Understanding the role of importance weighting for deep learningSpotlight57 citations
490. Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown DynamicsPoster57 citations
491. Estimating and Evaluating Regression Predictive Uncertainty in Deep Object DetectorsPoster56 citations
492. Generalization in data-driven models of primary visual cortexSpotlight56 citations
493. Rethinking the Role of Gradient-based Attribution Methods for Model InterpretabilityOral56 citations
494. Zero-shot Synthesis with Group-Supervised LearningPoster56 citations
495. Capturing Label Characteristics in VAEsPoster55 citations
496. Fast And Slow Learning Of Recurrent Independent MechanismsPoster55 citations
497. Interpreting and Boosting Dropout from a Game-Theoretic ViewPoster55 citations
498. Undistillable: Making A Nasty Teacher That CANNOT teach studentsSpotlight55 citations
499. A Block Minifloat Representation for Training Deep Neural NetworksPoster54 citations
500. Bidirectional Variational Inference for Non-Autoregressive Text-to-SpeechPoster54 citations
501. Clairvoyance: A Pipeline Toolkit for Medical Time SeriesPoster54 citations
502. Generative Time-series Modeling with Fourier FlowsPoster54 citations
503. IDF++: Analyzing and Improving Integer Discrete Flows for Lossless CompressionPoster54 citations
504. Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial TimeSpotlight54 citations
505. Self-supervised Visual Reinforcement Learning with Object-centric RepresentationsSpotlight54 citations
506. The inductive bias of ReLU networks on orthogonally separable dataPoster54 citations
507. Are wider nets better given the same number of parameters?Poster53 citations
508. Autoregressive Dynamics Models for Offline Policy Evaluation and OptimizationPoster53 citations
509. Deep Networks and the Multiple Manifold ProblemPoster53 citations
510. Multi-Level Local SGD: Distributed SGD for Heterogeneous Hierarchical NetworksPoster53 citations
511. NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose EstimationPoster53 citations
512. Reset-Free Lifelong Learning with Skill-Space PlanningPoster53 citations
513. Debiasing Concept-based Explanations with Causal AnalysisPoster52 citations
514. Efficient Transformers in Reinforcement Learning using Actor-Learner DistillationPoster52 citations
515. Hierarchical Autoregressive Modeling for Neural Video CompressionPoster52 citations
516. Learning Associative Inference Using Fast Weight MemoryPoster52 citations
517. On the Theory of Implicit Deep Learning: Global Convergence with Implicit LayersSpotlight52 citations
518. Sharper Generalization Bounds for Learning with Gradient-dominated Objective FunctionsPoster52 citations
519. Single-Timescale Actor-Critic Provably Finds Globally Optimal PolicyPoster52 citations
520. Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement LearningPoster51 citations
521. Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue SystemPoster51 citations
522. Uncertainty-aware Active Learning for Optimal Bayesian ClassifierPoster51 citations
523. Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and SamplingPoster50 citations
524. When does preconditioning help or hurt generalization?Poster50 citations
525. Why resampling outperforms reweighting for correcting sampling bias with stochastic gradientsPoster50 citations
526. Graph-Based Continual LearningSpotlight49 citations
527. HyperGrid Transformers: Towards A Single Model for Multiple TasksPoster49 citations
528. Isometric Propagation Network for Generalized Zero-shot LearningPoster49 citations
529. PC2WF: 3D Wireframe Reconstruction from Raw Point CloudsPoster49 citations
530. SMiRL: Surprise Minimizing Reinforcement Learning in Unstable EnvironmentsOral49 citations
531. Self-supervised Adversarial Robustness for the Low-label, High-data RegimePoster49 citations
532. Continual learning in recurrent neural networksPoster48 citations
533. Identifying nonlinear dynamical systems with multiple time scales and long-range dependenciesSpotlight48 citations
534. Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and FilteringPoster48 citations
535. Noise against noise: stochastic label noise helps combat inherent label noiseSpotlight48 citations
536. On Self-Supervised Image Representations for GAN EvaluationSpotlight48 citations
537. CPT: Efficient Deep Neural Network Training via Cyclic PrecisionSpotlight47 citations
538. Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning RatePoster47 citations
539. Efficient Certified Defenses Against Patch Attacks on Image ClassifiersPoster47 citations
540. Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature VisualizationPoster47 citations
541. Learning to live with Dale's principle: ANNs with separate excitatory and inhibitory unitsPoster47 citations
542. Multi-Class Uncertainty Calibration via Mutual Information Maximization-based BinningPoster47 citations
543. On the Critical Role of Conventions in Adaptive Human-AI CollaborationPoster47 citations
544. Overfitting for Fun and Profit: Instance-Adaptive Data CompressionPoster47 citations
545. Planning from Pixels using Inverse Dynamics ModelsPoster47 citations
546. Sliced Kernelized Stein DiscrepancyPoster47 citations
547. Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time AlgorithmsPoster47 citations
548. Categorical Normalizing Flows via Continuous TransformationsPoster46 citations
549. Generalization bounds via distillationSpotlight46 citations
550. Neural Delay Differential EquationsPoster46 citations
551. Efficient Generalized Spherical CNNsPoster45 citations
552. Lifelong Learning of Compositional StructuresPoster45 citations
553. Locally Free Weight Sharing for Network Width SearchSpotlight45 citations
554. Relating by Contrasting: A Data-efficient Framework for Multimodal Generative ModelsPoster45 citations
555. ResNet After All: Neural ODEs and Their Numerical SolutionPoster45 citations
556. Contrastive Explanations for Reinforcement Learning via Embedded Self PredictionsOral44 citations
557. Does enhanced shape bias improve neural network robustness to common corruptions?Poster44 citations
558. Self-supervised Representation Learning with Relative Predictive CodingPoster44 citations
559. Stabilized Medical Image AttacksSpotlight44 citations
560. Unsupervised Meta-Learning through Latent-Space Interpolation in Generative ModelsPoster44 citations
561. Acting in Delayed Environments with Non-Stationary Markov PoliciesPoster43 citations
562. Blending MPC & Value Function Approximation for Efficient Reinforcement LearningPoster43 citations
563. On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization AnalysisPoster43 citations
564. PDE-Driven Spatiotemporal DisentanglementPoster43 citations
565. Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient EstimatorOral43 citations
566. ChipNet: Budget-Aware Pruning with Heaviside Continuous ApproximationsPoster42 citations
567. Effective Abstract Reasoning with Dual-Contrast NetworkPoster42 citations
568. Entropic gradient descent algorithms and wide flat minimaPoster42 citations
569. Fast Geometric Projections for Local Robustness CertificationSpotlight42 citations
570. Nonseparable Symplectic Neural NetworksPoster42 citations
571. Overparameterisation and worst-case generalisation: friend or foe?Poster42 citations
572. Saliency is a Possible Red Herring When Diagnosing Poor GeneralizationPoster42 citations
573. Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence LearningPoster42 citations
574. DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation DialoguesPoster41 citations
575. Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution LayersPoster41 citations
576. Isometric Transformation Invariant and Equivariant Graph Convolutional NetworksPoster41 citations
577. Knowledge Distillation as Semiparametric InferencePoster41 citations
578. Separation and Concentration in Deep NetworksPoster41 citations
579. Wandering within a world: Online contextualized few-shot learningPoster41 citations
580. A Critique of Self-Expressive Deep Subspace ClusteringPoster40 citations
581. Can a Fruit Fly Learn Word Embeddings?Poster40 citations
582. Learning Manifold Patch-Based Representations of Man-Made ShapesPoster40 citations
583. Learning advanced mathematical computations from examplesPoster40 citations
584. Loss Function Discovery for Object Detection via Convergence-Simulation Driven SearchPoster40 citations
585. Multiscale Score Matching for Out-of-Distribution DetectionPoster40 citations
586. Neural networks with late-phase weightsPoster40 citations
587. Universal approximation power of deep residual neural networks via nonlinear control theoryPoster40 citations
588. gradSim: Differentiable simulation for system identification and visuomotor controlPoster40 citations
589. Disentangled Recurrent Wasserstein AutoencoderSpotlight39 citations
590. Implicit Normalizing FlowsSpotlight39 citations
591. Information Laundering for Model PrivacySpotlight39 citations
592. Local Convergence Analysis of Gradient Descent Ascent with Finite Timescale SeparationPoster39 citations
593. Private Post-GAN BoostingPoster39 citations
594. Bayesian Context Aggregation for Neural ProcessesPoster38 citations
595. For self-supervised learning, Rationality implies generalization, provablyPoster38 citations
596. Learning "What-if" Explanations for Sequential Decision-MakingPoster38 citations
597. Modeling the Second Player in Distributionally Robust OptimizationPoster38 citations
598. Contextual Dropout: An Efficient Sample-Dependent Dropout ModulePoster37 citations
599. Effective and Efficient Vote Attack on Capsule NetworksPoster37 citations
600. Group Equivariant Generative Adversarial NetworksPoster37 citations
601. Iterated learning for emergent systematicity in VQAOral37 citations
602. Latent Convergent Cross MappingPoster37 citations
603. Protecting DNNs from Theft using an Ensemble of Diverse ModelsPoster37 citations
604. Proximal Gradient Descent-Ascent: Variable Convergence under KŁ GeometryPoster37 citations
605. Understanding Over-parameterization in Generative Adversarial NetworksPoster37 citations
606. CompOFA – Compound Once-For-All Networks for Faster Multi-Platform DeploymentPoster36 citations
607. Differentiable Trust Region Layers for Deep Reinforcement LearningPoster36 citations
608. Improving VAEs' Robustness to Adversarial AttackPoster36 citations
609. MoVie: Revisiting Modulated Convolutions for Visual Counting and BeyondPoster36 citations
610. On the Impossibility of Global Convergence in Multi-Loss OptimizationPoster36 citations
611. PAC Confidence Predictions for Deep Neural Network ClassifiersPoster36 citations
612. Taming GANs with Lookahead-MinmaxPoster36 citations
613. What they do when in doubt: a study of inductive biases in seq2seq learnersPoster36 citations
614. Adaptive Procedural Task Generation for Hard-Exploration ProblemsPoster35 citations
615. Estimating Lipschitz constants of monotone deep equilibrium modelsPoster35 citations
616. GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy ImagesPoster35 citations
617. Individually Fair RankingsPoster35 citations
618. Learning A Minimax Optimizer: A Pilot StudyPoster35 citations
619. Learning Structural Edits via Incremental Tree TransformationsPoster35 citations
620. Multi-timescale Representation Learning in LSTM Language ModelsPoster35 citations
621. Randomized Automatic DifferentiationOral35 citations
622. Genetic Soft Updates for Policy Evolution in Deep Reinforcement LearningPoster34 citations
623. Learning-based Support Estimation in Sublinear TimeSpotlight34 citations
624. Rapid Task-Solving in Novel EnvironmentsPoster34 citations
625. Towards Robust Neural Networks via Close-loop ControlPoster34 citations
626. Unsupervised Discovery of 3D Physical Objects from VideoPoster34 citations
627. Collective Robustness Certificates: Exploiting Interdependence in Graph Neural NetworksPoster33 citations
628. Deep Repulsive Clustering of Ordered Data Based on Order-Identity DecompositionPoster33 citations
629. ECONOMIC HYPERPARAMETER OPTIMIZATION WITH BLENDED SEARCH STRATEGYPoster33 citations
630. Meta Back-TranslationPoster33 citations
631. Property Controllable Variational Autoencoder via Invertible Mutual DependencePoster33 citations
632. Semi-supervised Keypoint LocalizationPoster33 citations
633. Auto Seg-Loss: Searching Metric Surrogates for Semantic SegmentationPoster32 citations
634. Learning Parametrised Graph Shift OperatorsPoster32 citations
635. Molecule Optimization by Explainable EvolutionPoster32 citations
636. Mutual Information State Intrinsic ControlSpotlight32 citations
637. Provably robust classification of adversarial examples with detectionPoster32 citations
638. Revisiting Hierarchical Approach for Persistent Long-Term Video PredictionPoster32 citations
639. Unsupervised Object Keypoint Learning using Local Spatial PredictabilitySpotlight32 citations
640. AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the FlyPoster31 citations
641. Convex Regularization behind Neural ReconstructionPoster31 citations
642. Decentralized Attribution of Generative ModelsPoster31 citations
643. Evaluating the Disentanglement of Deep Generative Models through Manifold TopologyPoster31 citations
644. Global Convergence of Three-layer Neural Networks in the Mean Field RegimeOral31 citations
645. Group Equivariant Conditional Neural ProcessesPoster31 citations
646. Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov WassersteinPoster31 citations
647. Learning to Represent Action Values as a Hypergraph on the Action VerticesPoster31 citations
648. On Data-Augmentation and Consistency-Based Semi-Supervised LearningPoster31 citations
649. Sparse Quantized Spectral ClusteringSpotlight31 citations
650. Teaching with CommentariesPoster31 citations
651. AUXILIARY TASK UPDATE DECOMPOSITION: THE GOOD, THE BAD AND THE NEUTRALPoster30 citations
652. Explaining by Imitating: Understanding Decisions by Interpretable Policy LearningPoster30 citations
653. Large Batch Simulation for Deep Reinforcement LearningPoster30 citations
654. Learning Generalizable Visual Representations via Interactive GameplayOral30 citations
655. Learning to Generate 3D Shapes with Generative Cellular AutomataPoster30 citations
656. Memory Optimization for Deep NetworksSpotlight30 citations
657. Practical Massively Parallel Monte-Carlo Tree Search Applied to Molecular DesignPoster30 citations
658. Spatio-Temporal Graph Scattering TransformPoster30 citations
659. Calibration tests beyond classificationPoster29 citations
660. DeepAveragers: Offline Reinforcement Learning By Solving Derived Non-Parametric MDPsSpotlight29 citations
661. Discovering a set of policies for the worst case rewardSpotlight29 citations
662. Learning Task-General Representations with Generative Neuro-Symbolic ModelingPoster29 citations
663. Estimating informativeness of samples with Smooth Unique InformationPoster28 citations
664. Removing Undesirable Feature Contributions Using Out-of-Distribution DataPoster28 citations
665. Representing Partial Programs with Blended Abstract SemanticsPoster28 citations
666. Task-Agnostic Morphology EvolutionPoster28 citations
667. Efficient Wasserstein Natural Gradients for Reinforcement LearningPoster27 citations
668. Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' RulePoster27 citations
669. HyperDynamics: Meta-Learning Object and Agent Dynamics with HypernetworksPoster27 citations
670. Improving Transformation Invariance in Contrastive Representation LearningPoster27 citations
671. LiftPool: Bidirectional ConvNet PoolingPoster27 citations
672. Meta-Learning with Neural Tangent KernelsPoster27 citations
673. More or Less: When and How to Build Convolutional Neural Network EnsemblesPoster27 citations
674. No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep NetworksPoster27 citations
675. Solving Compositional Reinforcement Learning Problems via Task ReductionPoster27 citations
676. An Unsupervised Deep Learning Approach for Real-World Image DenoisingPoster26 citations
677. Balancing Constraints and Rewards with Meta-Gradient D4PGPoster26 citations
678. Conformation-Guided Molecular Representation with Hamiltonian Neural NetworksPoster26 citations
679. CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural NetworksPoster26 citations
680. Exploring the Uncertainty Properties of Neural Networks’ Implicit Priors in the Infinite-Width LimitPoster26 citations
681. Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable LearningPoster26 citations
682. Learning to Sample with Local and Global Contexts in Experience Replay BufferPoster26 citations
683. Parameter-Based Value FunctionsPoster26 citations
684. Statistical inference for individual fairnessPoster26 citations
685. Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust ExplorationPoster25 citations
686. Effective Distributed Learning with Random Features: Improved Bounds and AlgorithmsPoster25 citations
687. Predicting Infectiousness for Proactive Contact TracingSpotlight25 citations
688. Decoupling Global and Local Representations via Invertible Generative FlowsPoster24 citations
689. Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RLPoster24 citations
690. Emergent Road Rules In Multi-Agent Driving EnvironmentsPoster24 citations
691. Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations OnlinePoster24 citations
692. Iterative Empirical Game Solving via Single Policy Best ResponseSpotlight24 citations
693. Learning Value Functions in Deep Policy Gradients using Residual VariancePoster24 citations
694. New Bounds For Distributed Mean Estimation and Variance ReductionPoster24 citations
695. Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial ExamplesPoster24 citations
696. Reweighting Augmented Samples by Minimizing the Maximal Expected LossPoster24 citations
697. Anytime Sampling for Autoregressive Models via Ordered AutoencodingPoster23 citations
698. Cut out the annotator, keep the cutout: better segmentation with weak supervisionPoster23 citations
699. Improved Autoregressive Modeling with Distribution SmoothingOral23 citations
700. Meta-Learning of Structured Task Distributions in Humans and MachinesPoster23 citations
701. Probabilistic Numeric Convolutional Neural NetworksPoster23 citations
702. Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methodsSpotlight22 citations
703. Disentangling 3D Prototypical Networks for Few-Shot Concept LearningPoster22 citations
704. Extreme Memorization via Scale of InitializationPoster22 citations
705. Fooling a Complete Neural Network VerifierPoster22 citations
706. Identifying Physical Law of Hamiltonian Systems via Meta-LearningPoster22 citations
707. Interpreting Knowledge Graph Relation Representation from Word EmbeddingsPoster22 citations
708. Lossless Compression of Structured Convolutional Models via LiftingPoster22 citations
709. Meta-learning with negative learning ratesPoster22 citations
710. Practical Real Time Recurrent Learning with a Sparse ApproximationSpotlight22 citations
711. Diverse Video Generation using a Gaussian Process TriggerPoster21 citations
712. GAN "Steerability" without optimizationSpotlight21 citations
713. Hopper: Multi-hop Transformer for Spatiotemporal ReasoningPoster21 citations
714. Learning Better Structured Representations Using Low-rank Adaptive Label SmoothingPoster21 citations
715. Learning Task Decomposition with Ordered Memory Policy NetworkPoster21 citations
716. A Learning Theoretic Perspective on Local ExplainabilityPoster20 citations
717. Batch Reinforcement Learning Through Continuation MethodPoster20 citations
718. Combining Physics and Machine Learning for Network Flow EstimationPoster20 citations
719. Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regimePoster20 citations
720. Graph Convolution with Low-rank Learnable Local FiltersSpotlight20 citations
721. Graph Edit NetworksPoster20 citations
722. Large-width functional asymptotics for deep Gaussian neural networksPoster20 citations
723. Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable ModelsPoster20 citations
724. Representation Learning for Sequence Data with Deep Autoencoding Predictive ComponentsPoster20 citations
725. SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise LearningPoster20 citations
726. Self-Supervised Learning of Compressed Video RepresentationsPoster20 citations
727. Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor ProjectionsPoster20 citations
728. VA-RED$^2$: Video Adaptive Redundancy ReductionPoster20 citations
729. Activation-level uncertainty in deep neural networksPoster19 citations
730. Domain-Robust Visual Imitation Learning with Mutual Information ConstraintsPoster19 citations
731. Greedy-GQ with Variance Reduction: Finite-time Analysis and Improved ComplexityPoster19 citations
732. Individually Fair Gradient BoostingSpotlight19 citations
733. Latent Skill Planning for Exploration and TransferPoster19 citations
734. Learning to Deceive Knowledge Graph Augmented Models via Targeted PerturbationPoster19 citations
735. Physics-aware, probabilistic model order reduction with guaranteed stabilityPoster19 citations
736. Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point ProcessesOral19 citations
737. WrapNet: Neural Net Inference with Ultra-Low-Precision ArithmeticPoster19 citations
738. A Hypergradient Approach to Robust Regression without CorrespondencePoster18 citations
739. Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising PriorsSpotlight18 citations
740. Control-Aware Representations for Model-based Reinforcement LearningPoster18 citations
741. On the Universality of the Double Descent Peak in Ridgeless RegressionPoster18 citations
742. On the mapping between Hopfield networks and Restricted Boltzmann MachinesOral18 citations
743. One Network Fits All? Modular versus Monolithic Task Formulations in Neural NetworksPoster18 citations
744. Taking Notes on the Fly Helps Language Pre-TrainingPoster18 citations
745. The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels MethodsPoster18 citations
746. Certify or Predict: Boosting Certified Robustness with Compositional ArchitecturesPoster17 citations
747. Chaos of Learning Beyond Zero-sum and Coordination via Game DecompositionsPoster17 citations
748. Computational Separation Between Convolutional and Fully-Connected NetworksPoster17 citations
749. Deconstructing the Regularization of BatchNormPoster17 citations
750. Gradient Origin NetworksPoster17 citations
751. Learning Reasoning Paths over Semantic Graphs for Video-grounded DialoguesPoster17 citations
752. Neurally Augmented ALISTAPoster17 citations
753. The Role of Momentum Parameters in the Optimal Convergence of Adaptive Polyak's Heavy-ball MethodsPoster17 citations
754. DynaTune: Dynamic Tensor Program Optimization in Deep Neural Network CompilationPoster16 citations
755. Efficient Inference of Flexible Interaction in Spiking-neuron NetworksPoster16 citations
756. Factorizing Declarative and Procedural Knowledge in Structured, Dynamical EnvironmentsPoster16 citations
757. Influence Estimation for Generative Adversarial NetworksSpotlight16 citations
758. Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual BoundsPoster16 citations
759. Representation learning for improved interpretability and classification accuracy of clinical factors from EEGPoster16 citations
760. Variational Intrinsic Control RevisitedPoster16 citations
761. Go with the flow: Adaptive control for Neural ODEsPoster15 citations
762. Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose?Poster15 citations
763. Reducing the Computational Cost of Deep Generative Models with Binary Neural NetworksPoster15 citations
764. Regularized Inverse Reinforcement LearningSpotlight15 citations
765. SOLAR: Sparse Orthogonal Learned and Random EmbeddingsPoster15 citations
766. Set Prediction without Imposing Structure as Conditional Density EstimationPoster15 citations
767. The Traveling Observer Model: Multi-task Learning Through Spatial Variable EmbeddingsSpotlight15 citations
768. Theoretical bounds on estimation error for meta-learningPoster15 citations
769. Correcting experience replay for multi-agent communicationSpotlight14 citations
770. Learning to Make Decisions via Submodular RegularizationPoster14 citations
771. Monte-Carlo Planning and Learning with Language Action Value EstimatesPoster14 citations
772. No MCMC for me: Amortized sampling for fast and stable training of energy-based modelsPoster14 citations
773. On InstaHide, Phase Retrieval, and Sparse Matrix FactorizationPoster14 citations
774. Optimizing Memory Placement using Evolutionary Graph Reinforcement LearningPoster14 citations
775. The geometry of integration in text classification RNNsPoster14 citations
776. TropEx: An Algorithm for Extracting Linear Terms in Deep Neural NetworksPoster14 citations
777. Unsupervised Audiovisual Synthesis via Exemplar AutoencodersPoster14 citations
778. ANOCE: Analysis of Causal Effects with Multiple Mediators via Constrained Structural LearningPoster13 citations
779. Anchor & Transform: Learning Sparse Embeddings for Large VocabulariesPoster13 citations
780. Extracting Strong Policies for Robotics Tasks from Zero-Order Trajectory OptimizersPoster13 citations
781. Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple DomainsPoster13 citations
782. Learning Hyperbolic Representations of Topological FeaturesPoster13 citations
783. Usable Information and Evolution of Optimal Representations During TrainingPoster13 citations
784. Discovering Non-monotonic Autoregressive Orderings with Variational InferencePoster12 citations
785. Learning from Demonstration with Weakly Supervised DisentanglementPoster12 citations
786. Neural Networks for Learning Counterfactual G-Invariances from Single EnvironmentsPoster12 citations
787. Repurposing Pretrained Models for Robust Out-of-domain Few-Shot LearningPoster12 citations
788. Ringing ReLUs: Harmonic Distortion Analysis of Nonlinear Feedforward NetworksPoster12 citations
789. Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View SynthesisPoster11 citations
790. Contrastive Divergence Learning is a Time Reversal Adversarial GameSpotlight11 citations
791. Deciphering and Optimizing Multi-Task Learning: a Random Matrix ApproachSpotlight11 citations
792. Deep Learning meets Projective ClusteringPoster11 citations
793. Efficient Empowerment Estimation for Unsupervised StabilizationPoster11 citations
794. Filtered Inner Product Projection for Crosslingual Embedding AlignmentPoster11 citations
795. Learning a Latent Simplex in Input Sparsity TimeSpotlight11 citations
796. Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoFPoster11 citations
797. A Discriminative Gaussian Mixture Model with SparsityPoster10 citations
798. Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance ReductionPoster10 citations
799. Average-case Acceleration for Bilinear Games and Normal MatricesPoster10 citations
800. Conditional Generative Modeling via Learning the Latent SpacePoster10 citations
801. DINO: A Conditional Energy-Based GAN for Domain TranslationPoster10 citations
802. PolarNet: Learning to Optimize Polar Keypoints for Keypoint Based Object DetectionPoster10 citations
803. Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and AccuracySpotlight10 citations
804. Spatial Dependency Networks: Neural Layers for Improved Generative Image ModelingPoster10 citations
805. Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNsPoster10 citations
806. X2T: Training an X-to-Text Typing Interface with Online Learning from User FeedbackPoster10 citations
807. DDPNOpt: Differential Dynamic Programming Neural OptimizerSpotlight9 citations
808. Intraclass clustering: an implicit learning ability that regularizes DNNsPoster9 citations
809. Plan-Based Relaxed Reward Shaping for Goal-Directed TasksPoster9 citations
810. Provable Rich Observation Reinforcement Learning with Combinatorial Latent StatesPoster9 citations
811. Understanding the effects of data parallelism and sparsity on neural network trainingPoster9 citations
812. Contemplating Real-World Object ClassificationPoster8 citations
813. End-to-End Egospheric Spatial MemoryPoster8 citations
814. Local Search Algorithms for Rank-Constrained Convex OptimizationPoster8 citations
815. Simple Augmentation Goes a Long Way: ADRL for DNN QuantizationPoster8 citations
816. HalentNet: Multimodal Trajectory Forecasting with Hallucinative IntentsPoster7 citations
817. Improved Estimation of Concentration Under $\ell_p$-Norm Distance Metrics Using Half SpacesPoster7 citations
818. Learning What To Do by Simulating the PastPoster7 citations
819. Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output SpacesPoster7 citations
820. On the Dynamics of Training Attention ModelsPoster7 citations
821. UMEC: Unified model and embedding compression for efficient recommendation systemsPoster7 citations
822. A Temporal Kernel Approach for Deep Learning with Continuous-time InformationPoster6 citations
823. Fast convergence of stochastic subgradient method under interpolationPoster6 citations
824. IOT: Instance-wise Layer Reordering for Transformer StructuresPoster6 citations
825. NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-end Learning and ControlPoster6 citations
826. Prediction and generalisation over directed actions by grid cellsPoster6 citations
827. A teacher-student framework to distill future trajectoriesPoster5 citations
828. Faster Binary Embeddings for Preserving Euclidean DistancesPoster5 citations
829. Integrating Categorical Semantics into Unsupervised Domain TranslationPoster5 citations
830. Monotonic Kronecker-Factored LatticePoster5 citations
831. Predicting Classification Accuracy When Adding New Unobserved ClassesPoster5 citations
832. Private Image Reconstruction from System Side Channels Using Generative ModelsPoster5 citations
833. Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing FlowsPoster5 citations
834. Kanerva++: Extending the Kanerva Machine With Differentiable, Locally Block Allocated Latent MemoryPoster4 citations
835. Mapping the Timescale Organization of Neural Language ModelsPoster4 citations
836. Neural representation and generation for RNA secondary structuresPoster4 citations
837. Scaling Symbolic Methods using Gradients for Neural Model ExplanationPoster4 citations
838. Single-Photon Image ClassificationPoster4 citations
839. Sparse encoding for more-interpretable feature-selecting representations in probabilistic matrix factorizationPoster4 citations
840. Spatially Structured Recurrent ModulesPoster4 citations
841. A Design Space Study for LISTA and BeyondPoster3 citations
842. ARMOURED: Adversarially Robust MOdels using Unlabeled data by REgularizing DiversityPoster3 citations
843. Beyond Categorical Label Representations for Image ClassificationPoster3 citations
844. Multi-resolution modeling of a discrete stochastic process identifies causes of cancerPoster3 citations
845. SkipW: Resource Adaptable RNN with Strict Upper Computational LimitPoster3 citations
846. C-Learning: Horizon-Aware Cumulative Accessibility EstimationPoster2 citations
847. Differentiable Segmentation of SequencesPoster2 citations
848. Disambiguating Symbolic Expressions in Informal DocumentsPoster2 citations
849. Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization boundsPoster2 citations
850. Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear TimePoster2 citations
851. Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted DataPoster2 citations
852. What Can You Learn From Your Muscles? Learning Visual Representation from Human InteractionsPoster2 citations
853. Adapting to Reward Progressivity via Spectral Reinforcement LearningPoster1 citations
854. A Geometric Analysis of Deep Generative Image Models and Its ApplicationsPoster
855. Fidelity-based Deep Adiabatic SchedulingSpotlight
856. Mixed-Features Vectors and Subspace SplittingPoster
857. Regularization Matters in Policy Optimization - An Empirical Study on Continuous ControlSpotlight
858. Temporally-Extended ε-Greedy ExplorationPoster
859. Trusted Multi-View ClassificationPoster
860. UPDeT: Universal Multi-agent RL via Policy Decoupling with TransformersSpotlight

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