ICLR2024 Papers with Code
1.0.0
This warehouse aims to collect the latest research progress of ICLR, especially in LLM, involving all directions in the NLP field. This project will be updated from time to time for a long time.
Welcome to watch and fork! But it would be better to give it a star❤️.
Zhihu address: ShuYini
WeChat public account: AINLPer ( updated daily, welcome to follow )
1. Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
2. TabR: Tabular Deep Learning Meets Nearest Neighbors
3. Generative Judge for Evaluating Alignment
4. What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
5. Test-time Adaptation against Multi-modal Reliability Bias
6. Bellman Optimal Stepsize Straightening of Flow-Matching Models
7. On the Learnability of Watermarks for Language Models
8. Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction
9. Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
10. Multilingual Jailbreak Challenges in Large Language Models
11. Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
12. AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
13. Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery
14. CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects
15. TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
16.Graph Parsing Networks
17. KoLA: Carefully Benchmarking World Knowledge of Large Language Models
18. LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
19. Social-Transmotion: Promptable Human Trajectory Prediction
20. Robust Classification via Regression for Learning with Noisy Labels
21. Partitioning Message Passing for Graph Fraud Detection
22. Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
23. In-context Autoencoder for Context Compression in a Large Language Model
24. DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
25. Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
26. Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
27. RingAttention with Blockwise Transformers for Near-Infinite Context
28. Chain of Hindsight aligns Language Models with Feedback
29. Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
30. Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
31. RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
32. Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
33. Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
34. In-Context Learning through the Bayesian Prism
35. Neural Spectral Methods: Self-supervised learning in the spectral domain
36. SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
37. Kosmos-G: Generating Images in Context with Multimodal Large Language Models
38. Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
39. LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses
40. Energy-based Automated Model Evaluation
41. SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
42. ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
43. Data Debugging with Shapley Importance over Machine Learning Pipelines
44. RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
45. Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
46. Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
47. PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
48. Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
49. Pushing Boundaries: Mixup's Influence on Neural Collapse
50. Graph Transformers on EHRs: Better Representation Improves Downstream Performance
51. Uncertainty-aware Graph-based Hyperspectral Image Classification
52. On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
53. Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
54. UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
55. Exploring the Promise and Limits of Real-Time Recurrent Learning
56. Neural-Symbolic Recursive Machine for Systematic Generalization
57. Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
58. Are Models Biased on Text without Gender-related Language?
59. PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning
60. Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
61. Transformer-VQ: Linear-Time Transformers via Vector Quantization
62. Training Diffusion Models with Reinforcement Learning
63. Efficient Modulation for Vision Networks
64. Pre-training LiDAR-based 3D Object Detectors through Colorization
65. An Emulator for Fine-tuning Large Language Models using Small Language Models
66. Language Model Detectors Are Easily Optimized Against
67. Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models
68. GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
69. Stochastic Gradient Descent for Gaussian Processes Done Right
70. Fine-Tuning Language Models for Factuality
71. CNN Kernels Can Be the Best Shapelets
72. Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
73. Forward Learning of Graph Neural Networks
74. Does CLIP's generalization performance mainly stem from high train-test similarity?
75. Group Preference Optimization: Few-Shot Alignment of Large Language Models
76. L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
77. Llemma: An Open Language Model for Mathematics
78. Tree Search-Based Policy Optimization under Stochastic Execution Delay
79. Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
80. Context-Aware Meta-Learning
81. The Effectiveness of Random Forgetting for Robust Generalization
82. VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
83. Lie Group Decompositions for Equivariant Neural Networks
84. DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
85. To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets
86. On the Variance of Neural Network Training with respect to Test Sets and Distributions
87. GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries
88. Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
89. SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
90.Can Large Language Models Infer Causation from Correlation?
91. A Variational Perspective on Solving Inverse Problems with Diffusion Models
92. Layer-wise linear mode connectivity
93. NEFTune: Noisy Embeddings Improve Instruction Finetuning
94. Sparse MoE with Language Guided Routing for Multilingual Machine Translation
95. REFACTOR: Learning to Extract Theorems from Proofs
96. Detecting Pretraining Data from Large Language Models
97. Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
98. PubDef: Defending Against Transfer Attacks From Public Models
99. AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
100.Can LLM-Generated Misinformation Be Detected?
101. A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
102. Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference
103. Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
104. Eureka: Human-Level Reward Design via Coding Large Language Models
105. 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
106. Understanding Catastrophic Forgetting in Language Models via Implicit Inference
107. Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
108. What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine Similarity
109. Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
110. Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
111. Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
112. The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
113. AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
114. MixSATGEN: Learning Graph Mixing for SAT Instance Generation
115. PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
116. Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
117. Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
118. Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
119. Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
120. ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
121. Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation
122. Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
123. Score Models for Offline Goal-Conditioned Reinforcement Learning
124. USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
125. Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
126. Contrastive Difference Predictive Coding
127. MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data
128. HiGen: Hierarchical Graph Generative Networks
129. Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
130. PolyVoice: Language Models for Speech to Speech Translation
131. Adversarial Feature Map Pruning for Backdoor
132. EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models
133. CLEX: Continuous Length Extrapolation for Large Language Models
134. FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling
135. InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
136. Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
137. Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
138. Denoising Task Routing for Diffusion Models
139. Frequency-Aware Transformer for Learned Image Compression
140. Reward Model Ensembles Help Mitigation Overoptimization
141. Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
142. GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
143. Do Generated Data Always Help Contrastive Learning?
144. Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
145. Zero Bubble (Almost) Pipeline Parallelism
146. Exploring Weight Balancing on Long-Tailed Recognition Problem
147. Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
148. Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
149. ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF
150. Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
151. Attention-based Iterative Decomposition for Tensor Product Representation
152. Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models
153. Evaluating Language Model Agency Through Negotiations
154. VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation
155. Controlling Vision-Language Models for Multi-Task Image Restoration
156. Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
157. Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
158. Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains
159. AgentBench: Evaluating LLMs as Agents
160. Differentially Private Synthetic Data via Foundation Model APIs 1: Images
161. Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
162. Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification
163. Evaluating Large Language Models at Evaluating Instruction Following
164. Backdoor Contrastive Learning via Bi-level Trigger Optimization
165. MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
166. SafeDreamer: Safe Reinforcement Learning with World Models
167. Looped Transformers are Better at Learning Learning Algorithms
168. Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
169. Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
170.Explaining Time Series via Contrastive and Locally Sparse Perturbations
171. Dynamic Neural Response Tuning
172. Grounded Object-Centric Learning
173. On the Stability of Expressive Positional Encodings for Graphs
174. SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
175. Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
176. The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
177. Ensemble Distillation for Unsupervised Constituency Parsing
178. Training-free Multi-objective Diffusion Model for 3D Molecule Generation
179. Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
180. Non-negative Contrastive Learning
181. Understanding Domain Generalization: A Noise Robustness Perspective
182.Image Clustering Conditioned on Text Criteria
183. Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
184. Understanding Expressivity of GNN in Rule Learning
185. COLLIE: Systematic Construction of Constrained Text Generation Tasks
186. GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
187. Vanishing Gradients in Reinforcement Finetuning of Language Models
188. Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
189. Score Regularized Policy Optimization through Diffusion Behavior
190. Concept Bottleneck Generative Models
191. Robustifying and Boosting Training-Free Neural Architecture Search
192. MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
193. Learning Grounded Action Abstractions from Language
194. BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
195. $mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning
196. LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
197. Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
198. Deep Temporal Graph Clustering
199. CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding
200. Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
201. Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
202. WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
203. CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
204. Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
205. CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
206. Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
207. Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
208. Learning Planning Abstractions from Language
209. On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
210. Tailoring Self-Rationalizers with Multi-Reward Distillation
211. Building Cooperative Embodied Agents Modularly with Large Language Models
212. Fast Hyperboloid Decision Tree Algorithms
213. Few-Shot Detection of Machine-Generated Text using Style Representations
214. Massive Editing for Large Language Models via Meta Learning
215. Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
216, Safe and Robust Watermark Injection with A Single Ood Image
217. Defining Expertise: Applications to Treatment Effect Estimation
218, Alleviaating Exposure Bias in Diffusion Models Through Sampling with Shifted Time Steps
219, DiffTactile: A Physics-Based Differentiable Tactile Simulator for Contract-Robotic Manipulation
220, tangent transformers for composition, privacy and removal
221, Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
222, Universal Guidance for Diffusion Models
223. Quantifying Language Models' Sensitivity to SPURIOUS FEATURES in Prompt Design or: How I Learned to Start Worrying
224, Neur SDF Flow for 3D Reconstruction of Dynamic Scenes
225, REPHRASE, Augment, Reason: Visual Group of Questions for Vision-Language Models
226, Zoology: MeaSuring and IMPROVINGIVING RECALL in Efficient Language Models
227, Dynamic Sparse Training with Structudured Sparsity
228, Towards Training with Limits: Batch Normalization with Gradient Explosion
229, Curiosity-Driven Red-Teaming for Large Language Models
230, TACTIS-2: Better, Faster, Simpler Attentional Copulas for Multivar ass
231, Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
232, TIC-CLIP: Continual Training of Clip Models
233. Constrained Decoding for Cross-Lingual Label Projection
234, A Primal-Dual Approach to Solving Varizational Inequalities with General Constraints
235, Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words
236, ECOFLAP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
237. UndersTnding Reconstruction Attacks with the Neural Tangent Kernel and DataSet Distillation
238, adapting to distribution shift by visual domain prompt generation
239, Minigpt-4: Enhancing Vision-Language UndersTnding with Advanced LANGUAGE MODELS
240, Grokking as the Transition from Lazy to Rich Training Dynamics
241. Rethinking Backdoor Attacks on DataSet Distillation: A Kernel Method Perspective
242, Mixture of weak and Strong Experts on Graphs
243. Towards DIVERSE BeHAVIRS: a Benchmark for Imitation Learning with Human Demonstrations
244. ReconCiling Spatial and Temporal Abstractions for Goal Repositionation
245, LLM Augmented LLMS: Expanding Capabilities Through Composition
246.
247, Evaluating Repositionning Learning on the Protein Structure Universe
248, Nougat: Neural Optical Understnding for Academic Documens
249, Featup: A Model-Agnostic Framework for Features at any Resolution
250, Sparse Autoencoders Find Highly Interpretable Features in Language Models
251, OVOR: Oneprompt with Virtual Outlier Regularization for Rehearsal-Free Class-foundal Learning
252, Learning From Sparse Offline DataSets Via Conservative Density Estimation
253, quality-diversity through ai feedback
254, Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
255, openwebmath: an open dataset of high-Quality Mathematical Web Text
256. Robust Model-Based Optimization for Challenging Fitness Landscapes
257, Solving High Frequency and Multi-SCALE PDES With Gaussian PROCESSES
258, S $ 2 $ AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
259, Better Neur Pde Solvers Through Data-Free Mesh Movers
260, Conditional Variational Diffusion Models
261, Bend: Benchmarking DNA LANGUAGE MODELS on Biology Meaningful Tasks
262, Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks
263, Neur Optimal Transport with General Cost Functionals
264, A Topology Perspective on Demystifying Gnn-Based Link Prediction Performance
265, Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
266. Open The Black Box: Step-Based Policy Updates for Temporally-Correled Episodic Reinforcement Learning
267, Can we get the best of both binary neural networks and spiuking neural networks for efficient computer vision?
268, node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space
269, Ring-A-Bell! How RELIABLE is Concept Removal Methods for Diffusion Models?
270, Image Clustering Via The Principle of Rate Reduction in the Age of Pretrained Models
271, VECTOR-BASED RANDOM MATRIX Adaptation
272, PercedionClip: Visual Classification by Inferring and Conditioning on Contexts
273, Antgpt: Can Large Language Models Help Long-Term Anticipation from VideoS?
274, beno: Boundary-Embedded Neural Operators for Elliptic PDES
275, Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
276, Clifford Group Equivariant Simplicial Message Passing Networks
277, Unleashing Large-SCALE VIDEO Generative Pre-Training for Visual Robot Manipulation
278, VISION-BY-LANGUAGE for Training-Free Compositional Image Retrieval
279, GAIA: Zero-Shot Talking Avatar Generation
280, Robusttsf: Towards Theory and Design of Robust Time Series ForeCasting with Anomalies
281, SliceGPT: Compress Large Language Models by Deleting ROWS and Columns
282, Dorsal: Diffusion for Object-CENTRIC Reprerentations of Scenes
283, Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-Tuning
284, Leave-ONE-OET DISTISHABILITY in Machine Learning
285, Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
286, ENERGY-GUIDED ENTROPIC Neural Optimal Transport
287, neurl Architecture Retrieval
288, Removing Biase from Molecular Reprerentations Via Information Maximization
289, Faster Appromation of Probabilistic and Distributional Values Via Least Squares
290, TAB: Temport Accumulated Batch Normalization in Spiking Neural Networks
291, Rethinking The Uniformity Metric in Self-Supervned Learning
292, Diving segmentation Model into pixels
293, Hybrid Sharing for Multi-Label Image Classification
294, on Adversarial Training Wi
