ICLR 2024 Accepted Papers

The full list of 2,260 papers accepted at ICLR 2024 (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. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language ModelsPoster2,918 citations
2. SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisSpotlight2,203 citations
3. FlashAttention-2: Faster Attention with Better Parallelism and Work PartitioningPoster1,041 citations
4. iTransformer: Inverted Transformers Are Effective for Time Series ForecastingSpotlight912 citations
5. Let's Verify Step by StepPoster888 citations
6. MetaGPT: Meta Programming for A Multi-Agent Collaborative FrameworkOral872 citations
7. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific TuningSpotlight832 citations
8. Large Language Models as OptimizersPoster811 citations
9. WizardCoder: Empowering Code Large Language Models with Evol-InstructPoster661 citations
10. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsSpotlight639 citations
11. DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content CreationOral636 citations
12. Teaching Large Language Models to Self-DebugPoster636 citations
13. MVDream: Multi-view Diffusion for 3D GenerationPoster630 citations
14. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language ModelsSpotlight613 citations
15. Efficient Streaming Language Models with Attention SinksPoster598 citations
16. A Simple and Effective Pruning Approach for Large Language ModelsPoster582 citations
17. Time-LLM: Time Series Forecasting by Reprogramming Large Language ModelsPoster577 citations
18. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Oral564 citations
19. PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image SynthesisSpotlight546 citations
20. MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual ContextsOral541 citations
21. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionOral517 citations
22. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsPoster508 citations
23. SWE-bench: Can Language Models Resolve Real-world Github Issues?Oral500 citations
24. ChatEval: Towards Better LLM-based Evaluators through Multi-Agent DebatePoster461 citations
25. Large Language Models Cannot Self-Correct Reasoning YetPoster431 citations
26. LRM: Large Reconstruction Model for Single Image to 3DOral411 citations
27. Eureka: Human-Level Reward Design via Coding Large Language ModelsPoster380 citations
28. MiniLLM: Knowledge Distillation of Large Language ModelsPoster375 citations
29. WebArena: A Realistic Web Environment for Building Autonomous AgentsPoster363 citations
30. LongLoRA: Efficient Fine-tuning of Long-Context Large Language ModelsOral360 citations
31. Vision Transformers Need RegistersOral360 citations
32. Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion PriorsPoster356 citations
33. Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMsPoster355 citations
34. YaRN: Efficient Context Window Extension of Large Language ModelsPoster352 citations
35. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive CritiquingPoster347 citations
36. AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent BehaviorsPoster335 citations
37. MAmmoTH: Building Math Generalist Models through Hybrid Instruction TuningSpotlight332 citations
38. Llemma: An Open Language Model for MathematicsPoster320 citations
39. Safe RLHF: Safe Reinforcement Learning from Human FeedbackSpotlight320 citations
40. Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingPoster318 citations
41. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language ModelsPoster314 citations
42. Training Diffusion Models with Reinforcement LearningPoster303 citations
43. Ferret: Refer and Ground Anything Anywhere at Any GranularitySpotlight300 citations
44. Language Model Beats Diffusion - Tokenizer is key to visual generationPoster296 citations
45. InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and GenerationSpotlight295 citations
46. Catastrophic Jailbreak of Open-source LLMs via Exploiting GenerationSpotlight292 citations
47. Detecting Pretraining Data from Large Language ModelsPoster287 citations
48. SALMONN: Towards Generic Hearing Abilities for Large Language ModelsPoster286 citations
49. Effective Data Augmentation With Diffusion ModelsPoster284 citations
50. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge GraphPoster275 citations
51. ControlVideo: Training-free Controllable Text-to-video GenerationPoster271 citations
52. Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction TuningPoster270 citations
53. Sheared LLaMA: Accelerating Language Model Pre-training via Structured PruningPoster270 citations
54. Emu: Generative Pretraining in MultimodalityPoster269 citations
55. DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species GenomesPoster262 citations
56. NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing SynthesizersSpotlight260 citations
57. Sparse Autoencoders Find Highly Interpretable Features in Language ModelsPoster257 citations
58. Universal Guidance for Diffusion ModelsPoster257 citations
59. Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction ModelPoster250 citations
60. Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian SplattingPoster248 citations
61. Language Models Represent Space and TimePoster247 citations
62. SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight CompressionPoster247 citations
63. OmniQuant: Omnidirectionally Calibrated Quantization for Large Language ModelsSpotlight246 citations
64. Analyzing and Mitigating Object Hallucination in Large Vision-Language ModelsPoster244 citations
65. TokenFlow: Consistent Diffusion Features for Consistent Video EditingPoster244 citations
66. Building Cooperative Embodied Agents Modularly with Large Language ModelsPoster238 citations
67. Multilingual Jailbreak Challenges in Large Language ModelsPoster238 citations
68. GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via CipherPoster236 citations
69. AlpaGasus: Training a Better Alpaca with Fewer DataPoster235 citations
70. OctoPack: Instruction Tuning Code Large Language ModelsSpotlight235 citations
71. A Real-World WebAgent with Planning, Long Context Understanding, and Program SynthesisOral233 citations
72. Personalize Segment Anything Model with One ShotPoster233 citations
73. OpenChat: Advancing Open-source Language Models with Mixed-Quality DataPoster232 citations
74. Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningPoster231 citations
75. Self-Alignment with Instruction BacktranslationOral230 citations
76. Human Motion Diffusion as a Generative PriorPoster229 citations
77. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning OptimizationPoster227 citations
78. The Alignment Problem from a Deep Learning PerspectivePoster225 citations
79. Towards Understanding Sycophancy in Language ModelsPoster225 citations
80. SyncDreamer: Generating Multiview-consistent Images from a Single-view ImageSpotlight223 citations
81. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic AlignmentPoster222 citations
82. InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationPoster217 citations
83. Large Language Models Are Not Robust Multiple Choice SelectorsSpotlight215 citations
84. Can LLM-Generated Misinformation Be Detected?Poster214 citations
85. TimeMixer: Decomposable Multiscale Mixing for Time Series ForecastingPoster210 citations
86. Model Tells You What to Discard: Adaptive KV Cache Compression for LLMsOral202 citations
87. RingAttention with Blockwise Transformers for Near-Infinite ContextPoster202 citations
88. TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series ForecastingPoster202 citations
89. Statistical Rejection Sampling Improves Preference OptimizationPoster199 citations
90. DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language ModelsPoster197 citations
91. Prometheus: Inducing Fine-Grained Evaluation Capability in Language ModelsPoster193 citations
92. ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem SolvingPoster193 citations
93. DreamLLM: Synergistic Multimodal Comprehension and CreationSpotlight187 citations
94. VeRA: Vector-based Random Matrix AdaptationPoster184 citations
95. Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and MitigationPoster181 citations
96. Self-Consuming Generative Models Go MADPoster179 citations
97. LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language ModelsOral178 citations
98. WildChat: 1M ChatGPT Interaction Logs in the WildSpotlight178 citations
99. Listen, Think, and UnderstandPoster177 citations
100. AgentBench: Evaluating LLMs as AgentsPoster175 citations
101. WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex InstructionsPoster175 citations
102. Large Language Models as Tool MakersPoster174 citations
103. The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”Poster174 citations
104. Language Modeling Is CompressionPoster173 citations
105. Talk like a Graph: Encoding Graphs for Large Language ModelsPoster173 citations
106. Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow InstructionsPoster172 citations
107. Making Retrieval-Augmented Language Models Robust to Irrelevant ContextPoster171 citations
108. Retrieval meets Long Context Large Language ModelsPoster171 citations
109. Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of DiffusionPoster169 citations
110. The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context LearningPoster169 citations
111. What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction TuningPoster169 citations
112. QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language ModelsPoster168 citations
113. Demystifying CLIP DataSpotlight166 citations
114. Finite Scalar Quantization: VQ-VAE Made SimplePoster166 citations
115. Provable Robust Watermarking for AI-Generated TextPoster166 citations
116. Beyond Memorization: Violating Privacy via Inference with Large Language ModelsSpotlight164 citations
117. EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree RepresentationsPoster164 citations
118. SliceGPT: Compress Large Language Models by Deleting Rows and ColumnsPoster164 citations
119. Evaluating Large Language Models at Evaluating Instruction FollowingPoster163 citations
120. Fine-Tuning Language Models for FactualityPoster162 citations
121. LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation DatasetSpotlight160 citations
122. Take a Step Back: Evoking Reasoning via Abstraction in Large Language ModelsPoster157 citations
123. A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language ModelsPoster156 citations
124. Chain of Hindsight aligns Language Models with FeedbackPoster155 citations
125. Conformal Risk ControlSpotlight155 citations
126. Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic LocalizationSpotlight154 citations
127. Data Filtering NetworksPoster153 citations
128. Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-VerificationPoster153 citations
129. Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level VisionSpotlight151 citations
130. Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingPoster151 citations
131. DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction ModelSpotlight150 citations
132. DragonDiffusion: Enabling Drag-style Manipulation on Diffusion ModelsSpotlight149 citations
133. AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly DetectionPoster148 citations
134. Improved Techniques for Training Consistency ModelsOral148 citations
135. SOTOPIA: Interactive Evaluation for Social Intelligence in Language AgentsSpotlight148 citations
136. Function Vectors in Large Language ModelsPoster147 citations
137. Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language ModelsSpotlight147 citations
138. Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability CurvaturePoster146 citations
139. LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language ModelsPoster144 citations
140. In-context Autoencoder for Context Compression in a Large Language ModelPoster143 citations
141. Time Travel in LLMs: Tracing Data Contamination in Large Language ModelsSpotlight143 citations
142. RA-DIT: Retrieval-Augmented Dual Instruction TuningPoster142 citations
143. From Sparse to Soft Mixtures of ExpertsSpotlight138 citations
144. Proving Test Set Contamination in Black-Box Language ModelsOral137 citations
145. Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D GenerationPoster136 citations
146. SpeechTokenizer: Unified Speech Tokenizer for Speech Language ModelsPoster136 citations
147. Directly Fine-Tuning Diffusion Models on Differentiable RewardsPoster135 citations
148. MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language FeedbackPoster135 citations
149. When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning MethodPoster135 citations
150. Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge ConflictsSpotlight134 citations
151. RepoBench: Benchmarking Repository-Level Code Auto-Completion SystemsPoster134 citations
152. UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity RecognitionPoster133 citations
153. Vision-Language Foundation Models as Effective Robot ImitatorsSpotlight133 citations
154. Learning Interactive Real-World SimulatorsOral132 citations
155. What Algorithms can Transformers Learn? A Study in Length GeneralizationPoster132 citations
156. SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and GenerationSpotlight130 citations
157. Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation LearningPoster129 citations
158. KoLA: Carefully Benchmarking World Knowledge of Large Language ModelsPoster129 citations
159. RAPTOR: Recursive Abstractive Processing for Tree-Organized RetrievalPoster129 citations
160. SEINE: Short-to-Long Video Diffusion Model for Generative Transition and PredictionPoster129 citations
161. Unbiased Watermark for Large Language ModelsSpotlight129 citations
162. ModernTCN: A Modern Pure Convolution Structure for General Time Series AnalysisSpotlight128 citations
163. TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time SeriesPoster126 citations
164. Can Large Language Models Infer Causation from Correlation?Poster125 citations
165. GAIA: a benchmark for General AI AssistantsPoster125 citations
166. Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language ModelsPoster124 citations
167. FITS: Modeling Time Series with $10k$ ParametersSpotlight123 citations
168. Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion ModelsPoster123 citations
169. RAIN: Your Language Models Can Align Themselves without FinetuningPoster122 citations
170. AdaMerging: Adaptive Model Merging for Multi-Task LearningPoster121 citations
171. Understanding the Effects of RLHF on LLM Generalisation and DiversityPoster121 citations
172. MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingPoster120 citations
173. SaProt: Protein Language Modeling with Structure-aware VocabularySpotlight117 citations
174. TD-MPC2: Scalable, Robust World Models for Continuous ControlSpotlight117 citations
175. A Variational Perspective on Solving Inverse Problems with Diffusion ModelsPoster116 citations
176. Making LLaMA SEE and Draw with SEED TokenizerPoster116 citations
177. BooookScore: A systematic exploration of book-length summarization in the era of LLMsOral115 citations
178. Guiding Instruction-based Image Editing via Multimodal Large Language ModelsSpotlight115 citations
179. Identifying the Risks of LM Agents with an LM-Emulated SandboxSpotlight115 citations
180. PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt OptimizationPoster115 citations
181. SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3DPoster115 citations
182. Generative Judge for Evaluating AlignmentPoster114 citations
183. Mixture of LoRA ExpertsPoster114 citations
184. SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step ReasoningPoster114 citations
185. Nougat: Neural Optical Understanding for Academic DocumentsPoster113 citations
186. OmniControl: Control Any Joint at Any Time for Human Motion GenerationPoster113 citations
187. One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-AttentionPoster112 citations
188. Reward Model Ensembles Help Mitigate OveroptimizationPoster112 citations
189. Habitat 3.0: A Co-Habitat for Humans, Avatars, and RobotsPoster111 citations
190. Multimodal Web Navigation with Instruction-Finetuned Foundation ModelsPoster111 citations
191. PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of CodePoster111 citations
192. ReLoRA: High-Rank Training Through Low-Rank UpdatesPoster111 citations
193. DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion PriorPoster110 citations
194. Chain of Thought Empowers Transformers to Solve Inherently Serial ProblemsPoster109 citations
195. On-Policy Distillation of Language Models: Learning from Self-Generated MistakesPoster109 citations
196. Teaching Arithmetic to Small TransformersPoster108 citations
197. Chain-of-Table: Evolving Tables in the Reasoning Chain for Table UnderstandingPoster107 citations
198. Is Self-Repair a Silver Bullet for Code Generation?Poster106 citations
199. Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction TuningPoster106 citations
200. The Expressive Power of Transformers with Chain of ThoughtPoster105 citations
201. Hypothesis Search: Inductive Reasoning with Language ModelsPoster104 citations
202. Turning large language models into cognitive modelsPoster104 citations
203. MagicDrive: Street View Generation with Diverse 3D Geometry ControlPoster103 citations
204. Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion ModelsPoster102 citations
205. LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language ModelsOral102 citations
206. LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized AttentionPoster102 citations
207. Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMsPoster101 citations
208. PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape PredictionSpotlight101 citations
209. Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series ForecastingPoster101 citations
210. #InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language ModelsPoster100 citations
211. Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous SourcesPoster100 citations
212. DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated TextPoster100 citations
213. ZipIt! Merging Models from Different Tasks without TrainingPoster100 citations
214. Does Writing with Language Models Reduce Content Diversity?Poster99 citations
215. Knowledge Fusion of Large Language ModelsPoster99 citations
216. Uni3D: Exploring Unified 3D Representation at ScaleSpotlight99 citations
217. GoLLIE: Annotation Guidelines improve Zero-Shot Information-ExtractionPoster98 citations
218. MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical ReasoningPoster98 citations
219. Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion ModelsOral97 citations
220. Zipformer: A faster and better encoder for automatic speech recognitionOral97 citations
221. Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction AttacksSpotlight96 citations
222. Generalization in diffusion models arises from geometry-adaptive harmonic representationsOral96 citations
223. Matcher: Segment Anything with One Shot Using All-Purpose Feature MatchingPoster96 citations
224. GeoLLM: Extracting Geospatial Knowledge from Large Language ModelsPoster95 citations
225. The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open WorldPoster94 citations
226. What's In My Big Data?Spotlight94 citations
227. FLASK: Fine-grained Language Model Evaluation based on Alignment Skill SetsSpotlight93 citations
228. Interpreting CLIP's Image Representation via Text-Based DecompositionOral91 citations
229. INSIDE: LLMs' Internal States Retain the Power of Hallucination DetectionPoster90 citations
230. Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?Poster90 citations
231. GenSim: Generating Robotic Simulation Tasks via Large Language ModelsSpotlight89 citations
232. Unleashing Large-Scale Video Generative Pre-training for Visual Robot ManipulationPoster89 citations
233. Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image GenerationPoster88 citations
234. Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative InstructionsSpotlight88 citations
235. Kosmos-G: Generating Images in Context with Multimodal Large Language ModelsPoster87 citations
236. Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent SpaceOral87 citations
237. Solving Inverse Problems with Latent Diffusion Models via Hard Data ConsistencySpotlight87 citations
238. Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory MatchingPoster87 citations
239. AnyText: Multilingual Visual Text Generation and EditingSpotlight86 citations
240. Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity TheorySpotlight86 citations
241. DistillSpec: Improving Speculative Decoding via Knowledge DistillationPoster86 citations
242. Tensor Trust: Interpretable Prompt Injection Attacks from an Online GameSpotlight86 citations
243. Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual TokenizationPoster86 citations
244. ReLU Strikes Back: Exploiting Activation Sparsity in Large Language ModelsOral85 citations
245. Text-to-3D with Classifier Score DistillationPoster85 citations
246. Towards Foundation Models for Knowledge Graph ReasoningPoster85 citations
247. Tag2Text: Guiding Vision-Language Model via Image TaggingPoster84 citations
248. Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesisPoster84 citations
249. FreeNoise: Tuning-Free Longer Video Diffusion via Noise ReschedulingPoster82 citations
250. Zoology: Measuring and Improving Recall in Efficient Language ModelsPoster82 citations
251. FasterViT: Fast Vision Transformers with Hierarchical AttentionPoster81 citations
252. OpenWebMath: An Open Dataset of High-Quality Mathematical Web TextPoster81 citations
253. Hybrid LLM: Cost-Efficient and Quality-Aware Query RoutingPoster80 citations
254. MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to UsePoster80 citations
255. Universal Jailbreak Backdoors from Poisoned Human FeedbackPoster80 citations
256. Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence ConstraintsSpotlight79 citations
257. Small-scale proxies for large-scale Transformer training instabilitiesOral79 citations
258. HyperAttention: Long-context Attention in Near-Linear TimePoster78 citations
259. Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language ModelsPoster78 citations
260. Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis RefinementOral78 citations
261. Towards Best Practices of Activation Patching in Language Models: Metrics and MethodsPoster78 citations
262. Fine-Tuned Language Models Generate Stable Inorganic Materials as TextPoster77 citations
263. Label-free Node Classification on Graphs with Large Language Models (LLMs)Poster77 citations
264. Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCISpotlight77 citations
265. Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic ChipsPoster77 citations
266. Deep Temporal Graph ClusteringPoster76 citations
267. Improving LoRA in Privacy-preserving Federated LearningPoster76 citations
268. Linearity of Relation Decoding in Transformer Language ModelsSpotlight76 citations
269. Retroformer: Retrospective Large Language Agents with Policy Gradient OptimizationSpotlight76 citations
270. SE(3)-Stochastic Flow Matching for Protein Backbone GenerationSpotlight76 citations
271. Think before you speak: Training Language Models With Pause TokensPoster76 citations
272. Vision-Language Models are Zero-Shot Reward Models for Reinforcement LearningPoster76 citations
273. BadChain: Backdoor Chain-of-Thought Prompting for Large Language ModelsPoster75 citations
274. Bayesian Low-rank Adaptation for Large Language ModelsPoster75 citations
275. Conformal Language ModelingPoster75 citations
276. Large Language Models as Generalizable Policies for Embodied TasksPoster75 citations
277. PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise TrainingPoster75 citations
278. FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editingPoster74 citations
279. Massive Editing for Large Language Models via Meta LearningPoster74 citations
280. LLM-grounded Video Diffusion ModelsPoster73 citations
281. Learning Performance-Improving Code EditsSpotlight73 citations
282. Noise-free Score DistillationPoster72 citations
283. SILO Language Models: Isolating Legal Risk In a Nonparametric DatastoreSpotlight72 citations
284. Unpaired Image-to-Image Translation via Neural Schrödinger BridgePoster72 citations
285. Curiosity-driven Red-teaming for Large Language ModelsPoster71 citations
286. Diffusion-TS: Interpretable Diffusion for General Time Series GenerationPoster71 citations
287. Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model EvaluationPoster71 citations
288. Single Motion DiffusionSpotlight71 citations
289. DiffusionSat: A Generative Foundation Model for Satellite ImageryPoster70 citations
290. How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?Spotlight70 citations
291. On the Reliability of Watermarks for Large Language ModelsPoster70 citations
292. RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective AugmentationPoster70 citations
293. Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged ObjectsPoster70 citations
294. PB-LLM: Partially Binarized Large Language ModelsPoster68 citations
295. QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language ModelsPoster68 citations
296. The Expressive Power of Low-Rank AdaptationPoster68 citations
297. CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense PredictionSpotlight67 citations
298. Understanding Catastrophic Forgetting in Language Models via Implicit InferencePoster67 citations
299. Amortizing intractable inference in large language modelsOral66 citations
300. Privacy-Preserving In-Context Learning with Differentially Private Few-Shot GenerationPoster66 citations
301. Unified Human-Scene Interaction via Prompted Chain-of-ContactsSpotlight66 citations
302. DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image GenerationPoster65 citations
303. MogaNet: Multi-order Gated Aggregation NetworkPoster65 citations
304. Neural Common Neighbor with Completion for Link PredictionPoster65 citations
305. SmartPlay : A Benchmark for LLMs as Intelligent AgentsPoster65 citations
306. Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer ControlPoster65 citations
307. Consistent4D: Consistent 360° Dynamic Object Generation from Monocular VideoPoster64 citations
308. Large Multilingual Models Pivot Zero-Shot Multimodal Learning across LanguagesSpotlight64 citations
309. Motif: Intrinsic Motivation from Artificial Intelligence FeedbackPoster64 citations
310. ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion ModelsSpotlight64 citations
311. The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank ReductionPoster64 citations
312. The mechanistic basis of data dependence and abrupt learning in an in-context classification taskOral64 citations
313. Vision-by-Language for Training-Free Compositional Image RetrievalPoster64 citations
314. Circuit Component Reuse Across Tasks in Transformer Language ModelsSpotlight63 citations
315. Consistency-guided Prompt Learning for Vision-Language ModelsPoster63 citations
316. Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient ReasoningPoster63 citations
317. CRAFT: Customizing LLMs by Creating and Retrieving from Specialized ToolsetsPoster62 citations
318. Large Language Models to Enhance Bayesian OptimizationPoster62 citations
319. Mechanistically analyzing the effects of fine-tuning on procedurally defined tasksPoster62 citations
320. Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMsSpotlight62 citations
321. How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with RepresentationsPoster61 citations
322. LEGO-Prover: Neural Theorem Proving with Growing LibrariesOral61 citations
323. VDT: General-purpose Video Diffusion Transformers via Mask ModelingPoster61 citations
324. BadEdit: Backdooring Large Language Models by Model EditingPoster60 citations
325. CARD: Channel Aligned Robust Blend Transformer for Time Series ForecastingPoster60 citations
326. Cameras as Rays: Pose Estimation via Ray DiffusionOral60 citations
327. DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion ModelsPoster60 citations
328. Improved sampling via learned diffusionsPoster60 citations
329. Large Language Models as Analogical ReasonersPoster60 citations
330. Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised PretrainingPoster60 citations
331. Denoising Diffusion Bridge ModelsPoster59 citations
332. HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion GuidancePoster59 citations
333. How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated QuestionsPoster59 citations
334. Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable SpacingsPoster59 citations
335. DFormer: Rethinking RGBD Representation Learning for Semantic SegmentationPoster58 citations
336. Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHFPoster58 citations
337. JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and AttentionPoster58 citations
338. Rethinking Model Ensemble in Transfer-based Adversarial AttacksPoster58 citations
339. Universal Humanoid Motion Representations for Physics-Based ControlSpotlight58 citations
340. ARGS: Alignment as Reward-Guided SearchPoster57 citations
341. AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?Poster57 citations
342. Parameter-Efficient Orthogonal Finetuning via Butterfly FactorizationPoster57 citations
343. Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete DiffusionPoster56 citations
344. LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and GenerationPoster56 citations
345. LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model FinetuningPoster56 citations
346. Language Model InversionPoster56 citations
347. Learning to Act from Actionless Videos through Dense CorrespondencesSpotlight56 citations
348. MMICL: Empowering Vision-language Model with Multi-Modal In-Context LearningPoster56 citations
349. On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMsOral56 citations
350. Scaling Laws of RoPE-based ExtrapolationPoster56 citations
351. Detecting, Explaining, and Mitigating Memorization in Diffusion ModelsOral55 citations
352. Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMsPoster55 citations
353. EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-SupervisionPoster55 citations
354. Flow Matching on General GeometriesOral55 citations
355. Recursive Generalization Transformer for Image Super-ResolutionPoster55 citations
356. Scalable Diffusion for Materials GenerationPoster55 citations
357. Tree-Planner: Efficient Close-loop Task Planning with Large Language ModelsPoster55 citations
358. Brain decoding: toward real-time reconstruction of visual perceptionPoster54 citations
359. Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering PerspectivePoster54 citations
360. Grounding Multimodal Large Language Models to the WorldPoster54 citations
361. Linear attention is (maybe) all you need (to understand Transformer optimization)Poster54 citations
362. MuSR: Testing the Limits of Chain-of-thought with Multistep Soft ReasoningSpotlight54 citations
363. Training Socially Aligned Language Models on Simulated Social InteractionsPoster54 citations
364. Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty RegularizationPoster53 citations
365. Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse ProblemsPoster53 citations
366. Matryoshka Diffusion ModelsPoster53 citations
367. NEFTune: Noisy Embeddings Improve Instruction FinetuningPoster53 citations
368. RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory SketchesSpotlight53 citations
369. Model Merging by Uncertainty-Based Gradient MatchingPoster52 citations
370. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* SearchPoster52 citations
371. Unveiling the Pitfalls of Knowledge Editing for Large Language ModelsPoster52 citations
372. Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt EngineeringPoster51 citations
373. HyperHuman: Hyper-Realistic Human Generation with Latent Structural DiffusionPoster51 citations
374. Text2Reward: Reward Shaping with Language Models for Reinforcement LearningSpotlight51 citations
375. Towards 3D Molecule-Text Interpretation in Language ModelsPoster51 citations
376. Chain-of-Experts: When LLMs Meet Complex Operations Research ProblemsPoster50 citations
377. FeatUp: A Model-Agnostic Framework for Features at Any ResolutionPoster50 citations
378. Manifold Preserving Guided DiffusionPoster50 citations
379. Masked Audio Generation using a Single Non-Autoregressive TransformerPoster50 citations
380. PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural NetworksPoster50 citations
381. Quality-Diversity through AI FeedbackPoster50 citations
382. Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote AlignmentPoster50 citations
383. Robust agents learn causal world modelsOral50 citations
384. Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything ModelPoster49 citations
385. Deep Confident Steps to New Pockets: Strategies for Docking GeneralizationPoster49 citations
386. DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model TrainingPoster49 citations
387. Evaluating the Zero-shot Robustness of Instruction-tuned Language ModelsSpotlight49 citations
388. Exploring Target Representations for Masked AutoencodersPoster49 citations
389. Fair and Efficient Contribution Valuation for Vertical Federated LearningPoster49 citations
390. Large-scale Training of Foundation Models for Wearable BiosignalsPoster49 citations
391. THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELSPoster49 citations
392. Towards image compression with perfect realism at ultra-low bitratesPoster49 citations
393. How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker ComputationSpotlight48 citations
394. Lemur: Harmonizing Natural Language and Code for Language AgentsSpotlight48 citations
395. Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics TasksPoster48 citations
396. The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax MimicryPoster48 citations
397. BEND: Benchmarking DNA Language Models on Biologically Meaningful TasksPoster47 citations
398. Functional Interpolation for Relative Positions improves Long Context TransformersPoster47 citations
399. One For All: Towards Training One Graph Model For All Classification TasksSpotlight47 citations
400. Plug-and-Play: An Efficient Post-training Pruning Method for Large Language ModelsPoster47 citations
401. Real3D-Portrait: One-shot Realistic 3D Talking Portrait SynthesisSpotlight47 citations
402. Robustness of AI-Image Detectors: Fundamental Limits and Practical AttacksPoster47 citations
403. STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series PredictionPoster47 citations
404. Seer: Language Instructed Video Prediction with Latent Diffusion ModelsPoster47 citations
405. True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement LearningPoster47 citations
406. An Emulator for Fine-tuning Large Language Models using Small Language ModelsPoster46 citations
407. An Extensible Framework for Open Heterogeneous Collaborative PerceptionPoster46 citations
408. An Unforgeable Publicly Verifiable Watermark for Large Language ModelsPoster46 citations
409. CLEX: Continuous Length Extrapolation for Large Language ModelsPoster46 citations
410. ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEsOral46 citations
411. From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property PredictionPoster46 citations
412. Inducing High Energy-Latency of Large Vision-Language Models with Verbose ImagesPoster46 citations
413. InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data PruningOral46 citations
414. Multi-Source Diffusion Models for Simultaneous Music Generation and SeparationOral46 citations
415. TorchRL: A data-driven decision-making library for PyTorchSpotlight46 citations
416. At Which Training Stage Does Code Data Help LLMs Reasoning?Spotlight45 citations
417. Confronting Reward Model Overoptimization with Constrained RLHFSpotlight45 citations
418. Finetuning Text-to-Image Diffusion Models for FairnessOral45 citations
419. Fusing Models with Complementary ExpertisePoster45 citations
420. On the Stability of Iterative Retraining of Generative Models on their own DataSpotlight45 citations
421. Overthinking the Truth: Understanding how Language Models Process False DemonstrationsSpotlight45 citations
422. Tensor Programs VI: Feature Learning in Infinite Depth Neural NetworksPoster45 citations
423. Controlling Vision-Language Models for Multi-Task Image RestorationPoster44 citations
424. DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt EngineerSpotlight44 citations
425. DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuningPoster44 citations
426. Divide and not forget: Ensemble of selectively trained experts in Continual LearningPoster44 citations
427. EasyTPP: Towards Open Benchmarking Temporal Point ProcessesPoster44 citations
428. EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsSpotlight44 citations
429. LEAP: Liberate Sparse-View 3D Modeling from Camera PosesPoster44 citations
430. LLM Augmented LLMs: Expanding Capabilities through CompositionPoster44 citations
431. Magnushammer: A Transformer-Based Approach to Premise SelectionPoster44 citations
432. OWL: A Large Language Model for IT OperationsPoster44 citations
433. On the Learnability of Watermarks for Language ModelsPoster44 citations
434. PromptTTS 2: Describing and Generating Voices with Text PromptPoster44 citations
435. Simplifying Transformer BlocksPoster44 citations
436. SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMsPoster44 citations
437. Transport meets Variational Inference: Controlled Monte Carlo DiffusionsPoster44 citations
438. Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete FunctionsOral44 citations
439. Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity TrackingPoster43 citations
440. Human Feedback is not Gold StandardPoster43 citations
441. Towards Seamless Adaptation of Pre-trained Models for Visual Place RecognitionPoster43 citations
442. ViDA: Homeostatic Visual Domain Adapter for Continual Test Time AdaptationPoster43 citations
443. Differentially Private Synthetic Data via Foundation Model APIs 1: ImagesPoster42 citations
444. Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation NetworksSpotlight42 citations
445. Intriguing Properties of Generative ClassifiersSpotlight42 citations
446. METRA: Scalable Unsupervised RL with Metric-Aware AbstractionOral42 citations
447. Multiscale Positive-Unlabeled Detection of AI-Generated TextsSpotlight42 citations
448. Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic PromptsPoster42 citations
449. Protein Discovery with Discrete Walk-Jump SamplingOral42 citations
450. Skeleton-of-Thought: Prompting LLMs for Efficient Parallel GenerationPoster42 citations
451. Circumventing Concept Erasure Methods For Text-To-Image Generative ModelsPoster41 citations
452. Faithful Explanations of Black-box NLP Models Using LLM-generated CounterfactualsPoster41 citations
453. Group Preference Optimization: Few-Shot Alignment of Large Language ModelsPoster41 citations
454. Language Model Self-improvement by Reinforcement Learning ContemplationPoster41 citations
455. Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech SynthesisPoster41 citations
456. Negative Label Guided OOD Detection with Pretrained Vision-Language ModelsSpotlight41 citations
457. Neural Optimal Transport with General Cost FunctionalsPoster41 citations
458. Provable Offline Preference-Based Reinforcement LearningSpotlight41 citations
459. Space Group Constrained Crystal GenerationPoster41 citations
460. Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM FinetuningSpotlight41 citations
461. A Benchmark for Learning to Translate a New Language from One Grammar BookSpotlight40 citations
462. Compressing LLMs: The Truth is Rarely Pure and Never SimplePoster40 citations
463. DyVal: Dynamic Evaluation of Large Language Models for Reasoning TasksSpotlight40 citations
464. FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action RecognitionPoster40 citations
465. Frozen Transformers in Language Models Are Effective Visual Encoder LayersSpotlight40 citations
466. LaneSegNet: Map Learning with Lane Segment Perception for Autonomous DrivingPoster40 citations
467. Learning to Embed Time Series Patches IndependentlyPoster40 citations
468. One-shot Empirical Privacy Estimation for Federated LearningOral40 citations
469. Privacy-Preserving In-Context Learning for Large Language ModelsPoster40 citations
470. Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMPoster40 citations
471. Successor Heads: Recurring, Interpretable Attention Heads In The WildPoster40 citations
472. Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language ModelsPoster39 citations
473. Graph Neural Networks for Learning Equivariant Representations of Neural NetworksOral39 citations
474. GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge GraphsPoster39 citations
475. Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion ModelsPoster39 citations
476. ImagenHub: Standardizing the evaluation of conditional image generation modelsPoster39 citations
477. Making Pre-trained Language Models Great on Tabular PredictionSpotlight39 citations
478. OMNI: Open-endedness via Models of human Notions of InterestingnessPoster39 citations
479. TabR: Tabular Deep Learning Meets Nearest NeighborsPoster39 citations
480. CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed SamplingSpotlight38 citations
481. CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-SpeechPoster38 citations
482. Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled FactorsSpotlight38 citations
483. Octavius: Mitigating Task Interference in MLLMs via LoRA-MoEPoster38 citations
484. Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival PredictionSpotlight38 citations
485. Relay Diffusion: Unifying diffusion process across resolutions for image synthesisSpotlight38 citations
486. Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task DatasetsPoster38 citations
487. UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal ModelingPoster38 citations
488. When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and LimitationsPoster38 citations
489. CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulesPoster37 citations
490. Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationPoster37 citations
491. Elucidating the Exposure Bias in Diffusion ModelsPoster37 citations
492. GROOT: Learning to Follow Instructions by Watching Gameplay VideosSpotlight37 citations
493. Graph Metanetworks for Processing Diverse Neural ArchitecturesSpotlight37 citations
494. In-Context Learning Learns Label Relationships but Is Not Conventional LearningPoster37 citations
495. Polynormer: Polynomial-Expressive Graph Transformer in Linear TimePoster37 citations
496. Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion ModelPoster37 citations
497. Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMsPoster37 citations
498. AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion ModelPoster36 citations
499. Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time StepsPoster36 citations
500. Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN ExpressivenessOral36 citations
501. Consistency Models as a Rich and Efficient Policy Class for Reinforcement LearningPoster36 citations
502. CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and SimplicitySpotlight36 citations
503. Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake AnalysisPoster36 citations
504. Improved Probabilistic Image-Text RepresentationsPoster36 citations
505. Language Model Cascades: Token-Level Uncertainty And BeyondPoster36 citations
506. Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing PolicySpotlight36 citations
507. On the Stability of Expressive Positional Encodings for GraphsPoster36 citations
508. Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language TranslationPoster36 citations
509. The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image EditingPoster36 citations
510. Variational Bayesian Last LayersSpotlight36 citations
511. Xformer: Hybrid X-Shaped Transformer for Image DenoisingPoster36 citations
512. An Efficient Membership Inference Attack for the Diffusion Model by Proximal InitializationPoster35 citations
513. An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language ModelsSpotlight35 citations
514. BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationPoster35 citations
515. Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?Poster35 citations
516. Faithful Vision-Language Interpretation via Concept Bottleneck ModelsPoster35 citations
517. Federated Recommendation with Additive PersonalizationPoster35 citations
518. InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph PriorSpotlight35 citations
519. Multi-View Causal Representation Learning with Partial ObservabilitySpotlight35 citations
520. Periodicity Decoupling Framework for Long-term Series ForecastingPoster35 citations
521. Plug-and-Play Policy Planner for Large Language Model Powered Dialogue AgentsPoster35 citations
522. Real-Fake: Effective Training Data Synthesis Through Distribution MatchingPoster35 citations
523. TiC-CLIP: Continual Training of CLIP ModelsPoster35 citations
524. Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking OraclesPoster35 citations
525. BrainLM: A foundation model for brain activity recordingsPoster34 citations
526. ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRFPoster34 citations
527. Generative Pre-training for Speech with Flow MatchingPoster34 citations
528. How do Language Models Bind Entities in Context?Poster34 citations
529. Local Search GFlowNetsSpotlight34 citations
530. Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion EstimatorsPoster34 citations
531. SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI ModelsPoster34 citations
532. Skip-Attention: Improving Vision Transformers by Paying Less AttentionPoster34 citations
533. T-MARS: Improving Visual Representations by Circumventing Text Feature LearningPoster34 citations
534. Benign Overfitting and Grokking in ReLU Networks for XOR Cluster DataPoster33 citations
535. Jointly Training Large Autoregressive Multimodal ModelsPoster33 citations
536. LLM-Assisted Code Cleaning For Training Accurate Code GeneratorsPoster33 citations
537. Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven PriorsOral33 citations
538. On Diffusion Modeling for Anomaly DetectionSpotlight33 citations
539. OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel ViewsPoster33 citations
540. Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RLPoster33 citations
541. Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading IndicatorsPoster33 citations
542. SEPT: Towards Efficient Scene Representation Learning for Motion PredictionPoster33 citations
543. SLiMe: Segment Like MePoster33 citations
544. The LLM SurgeonPoster33 citations
545. An LLM can Fool Itself: A Prompt-Based Adversarial AttackPoster32 citations
546. AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZPoster32 citations
547. DSPy: Compiling Declarative Language Model Calls into State-of-the-Art PipelinesSpotlight32 citations
548. Do Generated Data Always Help Contrastive Learning?Poster32 citations
549. Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language ModelsOral32 citations
550. LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed PromptsPoster32 citations
551. Learning Multi-Agent Communication from Graph Modeling PerspectivePoster32 citations
552. MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein EmbeddingSpotlight32 citations
553. Making RL with Preference-based Feedback Efficient via RandomizationPoster32 citations
554. Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery DetectionSpotlight32 citations
555. Towards Few-Shot Adaptation of Foundation Models via Multitask FinetuningPoster32 citations
556. AMAGO: Scalable In-Context Reinforcement Learning for Adaptive AgentsSpotlight31 citations
557. DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion ModelsPoster31 citations
558. Decoding Natural Images from EEG for Object RecognitionPoster31 citations
559. Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce GrokkingPoster31 citations
560. Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with AutoformalizationPoster31 citations
561. FedCDA: Federated Learning with Cross-rounds Divergence-aware AggregationPoster31 citations
562. Frequency-Aware Transformer for Learned Image CompressionPoster31 citations
563. In-Context Learning through the Bayesian PrismPoster31 citations
564. Large-Vocabulary 3D Diffusion Model with TransformerPoster31 citations
565. Prompt Gradient Projection for Continual LearningSpotlight31 citations
566. Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementPoster31 citations
567. Spurious Feature Diversification Improves Out-of-distribution GeneralizationPoster31 citations
568. Teaching Language Models to Hallucinate Less with Synthetic TasksPoster31 citations
569. Towards Non-Asymptotic Convergence for Diffusion-Based Generative ModelsPoster31 citations
570. Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign FeaturesSpotlight31 citations
571. V-DETR: DETR with Vertex Relative Position Encoding for 3D Object DetectionPoster31 citations
572. VCR-Graphormer: A Mini-batch Graph Transformer via Virtual ConnectionsPoster31 citations
573. C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature DispersionPoster30 citations
574. DrM: Mastering Visual Reinforcement Learning through Dormant Ratio MinimizationSpotlight30 citations
575. Learning with Mixture of Prototypes for Out-of-Distribution DetectionPoster30 citations
576. Lemur: Integrating Large Language Models in Automated Program VerificationPoster30 citations
577. Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear TimePoster30 citations
578. PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time AdaptationPoster30 citations
579. Partitioning Message Passing for Graph Fraud DetectionPoster30 citations
580. Raidar: geneRative AI Detection viA RewritingPoster30 citations
581. The Generative AI Paradox: “What It Can Create, It May Not Understand”Poster30 citations
582. TopoMLP: A Simple yet Strong Pipeline for Driving Topology ReasoningPoster30 citations
583. A Hard-to-Beat Baseline for Training-free CLIP-based AdaptationPoster29 citations
584. A Study of Bayesian Neural Network Surrogates for Bayesian OptimizationPoster29 citations
585. An operator preconditioning perspective on training in physics-informed machine learningPoster29 citations
586. Benchmarking and Improving Generator-Validator Consistency of Language ModelsPoster29 citations
587. COLLIE: Systematic Construction of Constrained Text Generation TasksPoster29 citations
588. Controlled Text Generation via Language Model ArithmeticSpotlight29 citations
589. Large Language Models are Efficient Learners of Noise-Robust Speech RecognitionSpotlight29 citations
590. Locality-Aware Graph Rewiring in GNNsPoster29 citations
591. Machine Unlearning for Image-to-Image Generative ModelsPoster29 citations
592. PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human FeedbackPoster29 citations
593. PINNACLE: PINN Adaptive ColLocation and Experimental points selectionSpotlight29 citations
594. Toward effective protection against diffusion-based mimicry through score distillationPoster29 citations
595. Understanding Addition in TransformersPoster29 citations
596. Understanding and Mitigating the Label Noise in Pre-training on Downstream TasksSpotlight29 citations
597. AffineQuant: Affine Transformation Quantization for Large Language ModelsPoster28 citations
598. Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?Poster28 citations
599. Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 WordsPoster28 citations
600. Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling LimitPoster28 citations
601. Dual RL: Unification and New Methods for Reinforcement and Imitation LearningSpotlight28 citations
602. Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object DetectionPoster28 citations
603. IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language ModelsPoster28 citations
604. Less is More: Fewer Interpretable Region via Submodular Subset SelectionOral28 citations
605. Leveraging Optimization for Adaptive Attacks on Image WatermarksPoster28 citations
606. MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View StereoPoster28 citations
607. RetroBridge: Modeling Retrosynthesis with Markov BridgesSpotlight28 citations
608. Reverse Diffusion Monte CarloPoster28 citations
609. Stochastic Controlled Averaging for Federated Learning with Communication CompressionSpotlight28 citations
610. VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPsPoster28 citations
611. Contrastive Preference Learning: Learning from Human Feedback without Reinforcement LearningPoster27 citations
612. Empirical Analysis of Model Selection for Heterogeneous Causal Effect EstimationSpotlight27 citations
613. It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech RecognitionPoster27 citations
614. Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXPoster27 citations
615. KW-Design: Pushing the Limit of Protein Design via Knowledge RefinementPoster27 citations
616. Learning to Act without ActionsSpotlight27 citations
617. Memorization Capacity of Multi-Head Attention in TransformersSpotlight27 citations
618. On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic ApproximationSpotlight27 citations
619. On the Foundations of Shortcut LearningSpotlight27 citations
620. Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion ModelsPoster27 citations
621. Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance KernelPoster27 citations
622. Reasoning with Latent Diffusion in Offline Reinforcement LearningPoster27 citations
623. SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-trainingSpotlight27 citations
624. Simple Hierarchical Planning with DiffusionPoster27 citations
625. Soft Contrastive Learning for Time SeriesSpotlight27 citations
626. Teach LLMs to Phish: Stealing Private Information from Language ModelsPoster27 citations
627. To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data ContaminationPoster27 citations
628. Unleashing the Power of Pre-trained Language Models for Offline Reinforcement LearningPoster27 citations
629. A Sublinear Adversarial Training AlgorithmPoster26 citations
630. Addressing Loss of Plasticity and Catastrophic Forgetting in Continual LearningPoster26 citations
631. Analysis of Learning a Flow-based Generative Model from Limited Sample ComplexityPoster26 citations
632. Bridging State and History Representations: Understanding Self-Predictive RLPoster26 citations
633. CausalLM is not optimal for in-context learningPoster26 citations
634. Effective pruning of web-scale datasets based on complexity of concept clustersPoster26 citations
635. FFB: A Fair Fairness Benchmark for In-Processing Group Fairness MethodsPoster26 citations
636. From Zero to Turbulence: Generative Modeling for 3D Flow SimulationPoster26 citations
637. GPAvatar: Generalizable and Precise Head Avatar from Image(s)Poster26 citations
638. Generalized Schrödinger Bridge MatchingPoster26 citations
639. Initializing Models with Larger OnesSpotlight26 citations
640. Knowledge Distillation Based on Transformed Teacher MatchingPoster26 citations
641. LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained DescriptorsPoster26 citations
642. MUSTARD: Mastering Uniform Synthesis of Theorem and Proof DataSpotlight26 citations
643. Momentum Benefits Non-iid Federated Learning Simply and ProvablyPoster26 citations
644. MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled ImagesPoster26 citations
645. Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit PredictionSpotlight26 citations
646. PTaRL: Prototype-based Tabular Representation Learning via Space CalibrationSpotlight26 citations
647. Patched Denoising Diffusion Models For High-Resolution Image SynthesisPoster26 citations
648. PolyVoice: Language Models for Speech to Speech TranslationPoster26 citations
649. Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open WorldsPoster26 citations
650. Transformer Fusion with Optimal TransportPoster26 citations
651. Unified Generative Modeling of 3D Molecules with Bayesian Flow NetworksOral26 citations
652. A Unified and General Framework for Continual LearningPoster25 citations
653. DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain AdaptionPoster25 citations
654. GIM: Learning Generalizable Image Matcher From Internet VideosSpotlight25 citations
655. How Does Unlabeled Data Provably Help Out-of-Distribution Detection?Poster25 citations
656. Image Translation as Diffusion Visual ProgrammersPoster25 citations
657. Intriguing Properties of Data Attribution on Diffusion ModelsPoster25 citations
658. Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics SimulationPoster25 citations
659. Mastering Memory Tasks with World ModelsOral25 citations
660. ODEFormer: Symbolic Regression of Dynamical Systems with TransformersSpotlight25 citations
661. PhyloGFN: Phylogenetic inference with generative flow networksPoster25 citations
662. Retrieval-Enhanced Contrastive Vision-Text ModelsPoster25 citations
663. Revisiting Link Prediction: a data perspectivePoster25 citations
664. SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action RecognitionSpotlight25 citations
665. CellPLM: Pre-training of Cell Language Model Beyond Single CellsPoster24 citations
666. Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited SupervisionSpotlight24 citations
667. DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context LearningPoster24 citations
668. Efficient Video Diffusion Models via Content-Frame Motion-Latent DecompositionPoster24 citations
669. Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation SpacePoster24 citations
670. FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor CoresPoster24 citations
671. Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3DPoster24 citations
672. Generative Sliced MMD Flows with Riesz KernelsPoster24 citations
673. GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data GenerationPoster24 citations
674. Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of ElectrocardiogramPoster24 citations
675. Improving Non-Transferable Representation Learning by Harnessing Content and StyleSpotlight24 citations
676. Learning to Reject with a Fixed Predictor: Application to DecontextualizationPoster24 citations
677. Multisize Dataset CondensationOral24 citations
678. Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule GenerationPoster24 citations
679. Parameter-Efficient Multi-Task Model Fusion with Partial LinearizationPoster24 citations
680. Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language ModelsPoster24 citations
681. Quadratic models for understanding catapult dynamics of neural networksPoster24 citations
682. R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image GenerationPoster24 citations
683. SALMON: Self-Alignment with Instructable Reward ModelsPoster24 citations
684. Scaling Laws for Sparsely-Connected Foundation ModelsSpotlight24 citations
685. TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained ModelsPoster24 citations
686. Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language ModelsPoster24 citations
687. The Trickle-down Impact of Reward Inconsistency on RLHFPoster24 citations
688. Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human DemonstrationsPoster24 citations
689. Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy OptimizationPoster24 citations
690. AGILE3D: Attention Guided Interactive Multi-object 3D SegmentationPoster23 citations
691. Beyond Imitation: Leveraging Fine-grained Quality Signals for AlignmentPoster23 citations
692. Curriculum reinforcement learning for quantum architecture search under hardware errorsPoster23 citations
693. Debiased Collaborative Filtering with Kernel-Based Causal BalancingSpotlight23 citations
694. Does CLIP’s generalization performance mainly stem from high train-test similarity?Poster23 citations
695. Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental LearningPoster23 citations
696. Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor ProductsSpotlight23 citations
697. Evaluating Language Model Agency Through NegotiationsPoster23 citations
698. GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising DiffusionPoster23 citations
699. How to Fine-Tune Vision Models with SGDPoster23 citations
700. Improving protein optimization with smoothed fitness landscapesPoster23 citations
701. Neural Network-Based Score Estimation in Diffusion Models: Optimization and GeneralizationPoster23 citations
702. PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial FiltersSpotlight23 citations
703. Provable Compositional Generalization for Object-Centric LearningOral23 citations
704. RLCD: Reinforcement Learning from Contrastive Distillation for LM AlignmentPoster23 citations
705. SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt TuningPoster23 citations
706. Str2Str: A Score-based Framework for Zero-shot Protein Conformation SamplingPoster23 citations
707. Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human FeedbackPoster23 citations
708. What does the Knowledge Neuron Thesis Have to do with Knowledge?Spotlight23 citations
709. Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion AttacksPoster22 citations
710. Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChainPoster22 citations
711. BioBridge: Bridging Biomedical Foundation Models via Knowledge GraphsPoster22 citations
712. Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language ModelsPoster22 citations
713. CoBIT: A Contrastive Bi-directional Image-Text Generation ModelPoster22 citations
714. Concept Bottleneck Generative ModelsPoster22 citations
715. Conversational Drug Editing Using Retrieval and Domain FeedbackPoster22 citations
716. DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D GenerationPoster22 citations
717. Efficient Modulation for Vision NetworksPoster22 citations
718. Embarrassingly Simple Dataset DistillationPoster22 citations
719. FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link PredictionPoster22 citations
720. Generative Learning for Financial Time Series with Irregular and Scale-Invariant PatternsSpotlight22 citations
721. HoloNets: Spectral Convolutions do extend to Directed GraphsPoster22 citations
722. Idempotent Generative NetworkPoster22 citations
723. Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videoOral22 citations
724. LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language ModelsPoster22 citations
725. Let Models Speak Ciphers: Multiagent Debate through EmbeddingsPoster22 citations
726. MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning ProcessPoster22 citations
727. Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance ReductionOral22 citations
728. Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization AnalysisPoster22 citations
729. MgNO: Efficient Parameterization of Linear Operators via MultigridPoster22 citations
730. OpenTab: Advancing Large Language Models as Open-domain Table ReasonersPoster22 citations
731. Out-of-Distribution Detection with Negative PromptsPoster22 citations
732. Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte CarloPoster22 citations
733. SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive BiasesSpotlight22 citations
734. SemiReward: A General Reward Model for Semi-supervised LearningPoster22 citations
735. Spatio-Temporal Few-Shot Learning via Diffusive Neural Network GenerationPoster22 citations
736. TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of ExpertsPoster22 citations
737. Tool-Augmented Reward ModelingSpotlight22 citations
738. CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide ImagesSpotlight21 citations
739. CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making AgentsSpotlight21 citations
740. DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic ManipulationPoster21 citations
741. Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop SchedulingPoster21 citations
742. Efficient and Scalable Graph Generation through Iterative Local ExpansionPoster21 citations
743. Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step ReasoningPoster21 citations
744. FedImpro: Measuring and Improving Client Update in Federated LearningPoster21 citations
745. Forward Learning with Top-Down Feedback: Empirical and Analytical CharacterizationPoster21 citations
746. Fully Hyperbolic Convolutional Neural Networks for Computer VisionPoster21 citations
747. GAIA: Zero-shot Talking Avatar GenerationPoster21 citations
748. Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot ResponsePoster21 citations
749. InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision GeneralistsPoster21 citations
750. Interpretable Diffusion via Information DecompositionPoster21 citations
751. Localizing and Editing Knowledge In Text-to-Image Generative ModelsPoster21 citations
752. MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction FollowingPoster21 citations
753. Multi-Resolution Diffusion Models for Time Series ForecastingPoster21 citations
754. Neuron Activation Coverage: Rethinking Out-of-distribution Detection and GeneralizationSpotlight21 citations
755. ReMasker: Imputing Tabular Data with Masked AutoencodingPoster21 citations
756. SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data AugmentationPoster21 citations
757. SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problemSpotlight21 citations
758. SafeDreamer: Safe Reinforcement Learning with World ModelsPoster21 citations
759. Scaling Laws for Associative MemoriesSpotlight21 citations
760. Smooth ECE: Principled Reliability Diagrams via Kernel SmoothingPoster21 citations
761. Test-Time Training on Nearest Neighbors for Large Language ModelsPoster21 citations
762. The Consensus Game: Language Model Generation via Equilibrium SearchSpotlight21 citations
763. Towards Codable Watermarking for Injecting Multi-Bits Information to LLMsPoster21 citations
764. Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series ForecastingPoster21 citations
765. Understanding In-Context Learning from RepetitionsPoster21 citations
766. Zero-Shot Robustification of Zero-Shot ModelsPoster21 citations
767. $\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified StatesPoster20 citations
768. Bespoke Solvers for Generative Flow ModelsSpotlight20 citations
769. Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.Poster20 citations
770. Consistent Video-to-Video Transfer Using Synthetic DatasetPoster20 citations
771. Contrastive Learning is Spectral Clustering on Similarity GraphPoster20 citations
772. Copula Conformal prediction for multi-step time series predictionPoster20 citations
773. Data Distillation Can Be Like Vodka: Distilling More Times For Better QualityPoster20 citations
774. Dynamic Sparse Training with Structured SparsityPoster20 citations
775. Early Neuron Alignment in Two-layer ReLU Networks with Small InitializationPoster20 citations
776. Early Stopping Against Label Noise Without Validation DataPoster20 citations
777. Energy-based Automated Model EvaluationPoster20 citations
778. FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image AnalysisPoster20 citations
779. Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement LearningPoster20 citations
780. Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory GenerationPoster20 citations
781. From Latent Graph to Latent Topology Inference: Differentiable Cell Complex ModulePoster20 citations
782. Graph Transformers on EHRs: Better Representation Improves Downstream PerformancePoster20 citations
783. Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rankSpotlight20 citations
784. Implicit regularization of deep residual networks towards neural ODEsSpotlight20 citations
785. Inherently Interpretable Time Series Classification via Multiple Instance LearningSpotlight20 citations
786. Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation PatchingPoster20 citations
787. Layer-wise linear mode connectivityPoster20 citations
788. MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework DesignPoster20 citations
789. Multi-Task Reinforcement Learning with Mixture of Orthogonal ExpertsPoster20 citations
790. Multi-granularity Correspondence Learning from Long-term Noisy VideosOral20 citations
791. NECO: NEural Collapse Based Out-of-distribution detectionPoster20 citations
792. NeuroBack: Improving CDCL SAT Solving using Graph Neural NetworksPoster20 citations
793. Protein Multimer Structure Prediction via Prompt LearningPoster20 citations
794. Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion ModelsPoster20 citations
795. RLIF: Interactive Imitation Learning as Reinforcement LearningPoster20 citations
796. Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language ModelsPoster20 citations
797. Score Regularized Policy Optimization through Diffusion BehaviorPoster20 citations
798. The Hidden Language of Diffusion ModelsPoster20 citations
799. Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning FrameworkSpotlight20 citations
800. Towards Green AI in Fine-tuning Large Language Models via Adaptive BackpropagationPoster20 citations
801. Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and BeyondPoster20 citations
802. Trajeglish: Traffic Modeling as Next-Token PredictionPoster20 citations
803. Transformer-VQ: Linear-Time Transformers via Vector QuantizationPoster20 citations
804. Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language ModelsPoster20 citations
805. A Simple Interpretable Transformer for Fine-Grained Image Classification and AnalysisPoster19 citations
806. AutoVP: An Automated Visual Prompting Framework and BenchmarkPoster19 citations
807. Batched Low-Rank Adaptation of Foundation ModelsOral19 citations
808. Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision MakingSpotlight19 citations
809. Deep Orthogonal Hypersphere Compression for Anomaly DetectionSpotlight19 citations
810. Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information DecompositionPoster19 citations
811. Denoising Diffusion Step-aware ModelsPoster19 citations
812. Discovering Temporally-Aware Reinforcement Learning AlgorithmsPoster19 citations
813. Dissecting learning and forgetting in language model finetuningPoster19 citations
814. Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance AccompanimentPoster19 citations
815. EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion ModelsPoster19 citations
816. ExeDec: Execution Decomposition for Compositional Generalization in Neural Program SynthesisOral19 citations
817. Few-Shot Detection of Machine-Generated Text using Style RepresentationsPoster19 citations
818. Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEsPoster19 citations
819. How connectivity structure shapes rich and lazy learning in neural circuitsPoster19 citations
820. LEMON: Lossless model expansionPoster19 citations
821. LILO: Learning Interpretable Libraries by Compressing and Documenting CodePoster19 citations
822. Learning Energy Decompositions for Partial Inference in GFlowNetsOral19 citations
823. Learning to design protein-protein interactions with enhanced generalizationPoster19 citations
824. Probabilistically Rewired Message-Passing Neural NetworksPoster19 citations
825. Query-Policy Misalignment in Preference-Based Reinforcement LearningSpotlight19 citations
826. Rethinking Complex Queries on Knowledge Graphs with Neural Link PredictorsPoster19 citations
827. Sentence-level Prompts Benefit Composed Image RetrievalSpotlight19 citations
828. Sin3DM: Learning a Diffusion Model from a Single 3D Textured ShapePoster19 citations
829. Structuring Representation Geometry with Rotationally Equivariant Contrastive LearningPoster19 citations
830. Supervised Knowledge Makes Large Language Models Better In-context LearnersPoster19 citations
831. Test-time Adaptation against Multi-modal Reliability BiasPoster19 citations
832. A Lightweight Method for Tackling Unknown Participation Statistics in Federated AveragingSpotlight18 citations
833. AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality PredictionPoster18 citations
834. Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learningPoster18 citations
835. CABINET: Content Relevance-based Noise Reduction for Table Question AnsweringSpotlight18 citations
836. CODE REPRESENTATION LEARNING AT SCALEPoster18 citations
837. Correlated Noise Provably Beats Independent Noise for Differentially Private LearningPoster18 citations
838. Demystifying Embedding Spaces using Large Language ModelsPoster18 citations
839. Don't Play Favorites: Minority Guidance for Diffusion ModelsPoster18 citations
840. Efficient Subgraph GNNs by Learning Effective Selection PoliciesPoster18 citations
841. Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated LearningPoster18 citations
842. GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing ModulesPoster18 citations
843. How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular DataPoster18 citations
844. Identifying Representations for Intervention ExtrapolationPoster18 citations
845. Light Schrödinger BridgePoster18 citations
846. Maximum Entropy Heterogeneous-Agent Reinforcement LearningSpotlight18 citations
847. Multimodal Learning Without Labeled Multimodal Data: Guarantees and ApplicationsPoster18 citations
848. Multimodal Molecular Pretraining via Modality BlendingPoster18 citations
849. Multimodal Patient Representation Learning with Missing Modalities and LabelsPoster18 citations
850. On the Provable Advantage of Unsupervised PretrainingSpotlight18 citations
851. Parametric Augmentation for Time Series Contrastive LearningPoster18 citations
852. Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributionsPoster18 citations
853. Subtractive Mixture Models via Squaring: Representation and LearningSpotlight18 citations
854. TOSS: High-quality Text-guided Novel View Synthesis from a Single ImagePoster18 citations
855. Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update CalibrationPoster18 citations
856. ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic SegmentationOral18 citations
857. "What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data SelectionOral17 citations
858. A Versatile Causal Discovery Framework to Allow Causally-Related Hidden VariablesPoster17 citations
859. Adaptive Rational Activations to Boost Deep Reinforcement LearningSpotlight17 citations
860. Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention MapsSpotlight17 citations
861. BatchPrompt: Accomplish more with lessPoster17 citations
862. Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual InformationPoster17 citations
863. Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource LanguagesPoster17 citations
864. CPPO: Continual Learning for Reinforcement Learning with Human FeedbackPoster17 citations
865. Constrained Bi-Level Optimization: Proximal Lagrangian Value Function Approach and Hessian-free AlgorithmSpotlight17 citations
866. DOS: Diverse Outlier Sampling for Out-of-Distribution DetectionPoster17 citations
867. Debiasing Algorithm through Model AdaptationPoster17 citations
868. Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic InterpretationsPoster17 citations
869. Energy-guided Entropic Neural Optimal TransportPoster17 citations
870. FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound ScalingPoster17 citations
871. Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion ModelsPoster17 citations
872. Graph Lottery Ticket AutomatedPoster17 citations
873. Looped Transformers are Better at Learning Learning AlgorithmsPoster17 citations
874. MOTOR: A Time-to-Event Foundation Model For Structured Medical RecordsSpotlight17 citations
875. Multi-Scale Representations by Varying Window Attention for Semantic SegmentationPoster17 citations
876. NOLA: Compressing LoRA using Linear Combination of Random BasisPoster17 citations
877. Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFacePoster17 citations
878. Non-Exchangeable Conformal Risk ControlPoster17 citations
879. OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental LearningPoster17 citations
880. Object centric architectures enable efficient causal representation learningPoster17 citations
881. On Differentially Private Federated Linear Contextual BanditsPoster17 citations
882. Pre-Training and Fine-Tuning Generative Flow NetworksSpotlight17 citations
883. Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation LearningPoster17 citations
884. Quasi-Monte Carlo for 3D Sliced WassersteinSpotlight17 citations
885. Revisit and Outstrip Entity Alignment: A Perspective of Generative ModelsPoster17 citations
886. Scalable Language Model with Generalized Continual LearningPoster17 citations
887. Sparse Model Soups: A Recipe for Improved Pruning via Model AveragingPoster17 citations
888. Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline DataSpotlight17 citations
889. Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series DataSpotlight17 citations
890. Statistical Perspective of Top-K Sparse Softmax Gating Mixture of ExpertsPoster17 citations
891. Submodular Reinforcement LearningSpotlight17 citations
892. The Generalization Gap in Offline Reinforcement LearningPoster17 citations
893. The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical ModelPoster17 citations
894. Towards a statistical theory of data selection under weak supervisionOral17 citations
895. Training Unbiased Diffusion Models From Biased DatasetPoster17 citations
896. Backdoor Federated Learning by Poisoning Backdoor-Critical LayersPoster16 citations
897. Bayesian Neural Controlled Differential Equations for Treatment Effect EstimationPoster16 citations
898. Benchmarking Algorithms for Federated Domain GeneralizationSpotlight16 citations
899. Class Incremental Learning via Likelihood Ratio Based Task PredictionPoster16 citations
900. CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative DecodingPoster16 citations
901. Complete and Efficient Graph Transformers for Crystal Material Property PredictionPoster16 citations
902. Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and EditingPoster16 citations
903. Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned GenerationPoster16 citations
904. Domain-Agnostic Molecular Generation with Chemical FeedbackPoster16 citations
905. DreamFlow: High-quality text-to-3D generation by Approximating Probability FlowSpotlight16 citations
906. ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language ModelsPoster16 citations
907. HYPO: Hyperspherical Out-Of-Distribution GeneralizationPoster16 citations
908. Harnessing Density Ratios for Online Reinforcement LearningSpotlight16 citations
909. How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion ModelsOral16 citations
910. Idempotence and Perceptual Image CompressionSpotlight16 citations
911. ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection AlgorithmsPoster16 citations
912. Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent DynamicsSpotlight16 citations
913. Learning Optimal Contracts: How to Exploit Small Action SpacesPoster16 citations
914. Lion Secretly Solves a Constrained Optimization: As Lyapunov PredictsSpotlight16 citations
915. LitCab: Lightweight Language Model Calibration over Short- and Long-form ResponsesPoster16 citations
916. Logical Languages Accepted by Transformer Encoders with Hard AttentionPoster16 citations
917. MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding MethodsPoster16 citations
918. MetaCoCo: A New Few-Shot Classification Benchmark with Spurious CorrelationPoster16 citations
919. Mirage: Model-agnostic Graph Distillation for Graph ClassificationPoster16 citations
920. ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient UpdateSpotlight16 citations
921. Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language ModelsPoster16 citations
922. Social-Transmotion: Promptable Human Trajectory PredictionPoster16 citations
923. SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous ManipulationPoster16 citations
924. Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and RegressionSpotlight16 citations
925. Understanding Certified Training with Interval Bound PropagationPoster16 citations
926. Understanding Convergence and Generalization in Federated Learning through Feature Learning TheoryPoster16 citations
927. UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data SciencePoster16 citations
928. Unprocessing Seven Years of Algorithmic FairnessOral16 citations
929. 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud PretrainingPoster15 citations
930. A Restoration Network as an Implicit PriorPoster15 citations
931. Active Test-Time Adaptation: Theoretical Analyses and An AlgorithmPoster15 citations
932. Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEsPoster15 citations
933. Adversarial Training Should Be Cast as a Non-Zero-Sum GamePoster15 citations
934. Benign Oscillation of Stochastic Gradient Descent with Large Learning RatePoster15 citations
935. CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?Poster15 citations
936. Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven ReasoningPoster15 citations
937. CausalTime: Realistically Generated Time-series for Benchmarking of Causal DiscoveryPoster15 citations
938. CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design EnvironmentPoster15 citations
939. Compressed Context Memory for Online Language Model InteractionPoster15 citations
940. ConR: Contrastive Regularizer for Deep Imbalanced RegressionPoster15 citations
941. Context-Aware Meta-LearningPoster15 citations
942. Contrastive Difference Predictive CodingPoster15 citations
943. DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular OptimizationPoster15 citations
944. Denoising Task Routing for Diffusion ModelsPoster15 citations
945. Distinguished In Uniform: Self-Attention Vs. Virtual NodesPoster15 citations
946. Dual-Encoders for Extreme Multi-label ClassificationPoster15 citations
947. Enhancing One-Shot Federated Learning Through Data and Ensemble Co-BoostingPoster15 citations
948. Exploring Diffusion Time-steps for Unsupervised Representation LearningPoster15 citations
949. FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSsPoster15 citations
950. Feature emergence via margin maximization: case studies in algebraic tasksSpotlight15 citations
951. GRANDE: Gradient-Based Decision Tree Ensembles for Tabular DataPoster15 citations
952. Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMsPoster15 citations
953. Ghost on the Shell: An Expressive Representation of General 3D ShapesOral15 citations
954. HAZARD Challenge: Embodied Decision Making in Dynamically Changing EnvironmentsPoster15 citations
955. Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMsPoster15 citations
956. Identifiable Latent Polynomial Causal Models through the Lens of ChangePoster15 citations
957. Image Clustering via the Principle of Rate Reduction in the Age of Pretrained ModelsPoster15 citations
958. Improving Convergence and Generalization Using Parameter SymmetriesOral15 citations
959. Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep ModelsPoster15 citations
960. Language Model Detectors Are Easily Optimized AgainstPoster15 citations
961. Learning the greatest common divisor: explaining transformer predictionsSpotlight15 citations
962. LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied AgentsPoster15 citations
963. Maximum Likelihood Estimation is All You Need for Well-Specified Covariate ShiftPoster15 citations
964. Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal LearningPoster15 citations
965. Parallelizing non-linear sequential models over the sequence lengthPoster15 citations
966. Pre-Training Goal-based Models for Sample-Efficient Reinforcement LearningOral15 citations
967. Provable Reward-Agnostic Preference-Based Reinforcement LearningSpotlight15 citations
968. Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement LearningSpotlight15 citations
969. Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training StagesPoster15 citations
970. SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear LayerPoster15 citations
971. SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional VideosPoster15 citations
972. SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation LearningPoster15 citations
973. Searching for High-Value Molecules Using Reinforcement Learning and TransformersPoster15 citations
974. Selective Visual Representations Improve Convergence and Generalization for Embodied AISpotlight15 citations
975. Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean SpeechPoster15 citations
976. Sliced Wasserstein Estimation with Control VariatesPoster15 citations
977. Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample ComplexityPoster15 citations
978. The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language ModelsPoster15 citations
979. Towards Robust Fidelity for Evaluating Explainability of Graph Neural NetworksPoster15 citations
980. USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance FieldsPoster15 citations
981. Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement LearningPoster15 citations
982. Understanding Transferable Representation Learning and Zero-shot Transfer in CLIPPoster15 citations
983. Variance-aware Regret Bounds for Stochastic Contextual Dueling BanditsPoster15 citations
984. Why is SAM Robust to Label Noise?Poster15 citations
985. Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical MLPoster15 citations
986. Zero and Few-shot Semantic Parsing with Ambiguous InputsPoster15 citations
987. A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural NetworksPoster14 citations
988. ASID: Active Exploration for System Identification in Robotic ManipulationOral14 citations
989. Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in TransformersPoster14 citations
990. Accurate Forgetting for Heterogeneous Federated Continual LearningPoster14 citations
991. An Efficient Tester-Learner for HalfspacesPoster14 citations
992. Clifford Group Equivariant Simplicial Message Passing NetworksPoster14 citations
993. Compositional Generative Inverse DesignSpotlight14 citations
994. Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement TasksPoster14 citations
995. Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AIPoster14 citations
996. Entity-Centric Reinforcement Learning for Object Manipulation from PixelsSpotlight14 citations
997. FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware SchedulerPoster14 citations
998. Federated Q-Learning: Linear Regret Speedup with Low Communication CostPoster14 citations
999. GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth BenchmarkingPoster14 citations
1000. Generative Modeling with Phase Stochastic BridgeOral14 citations

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