Skip to content
/ ICLR2025-Papers-with-Code Public

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

178 stars 9 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

yinizhilian/ICLR2025-Papers-with-Code

BranchesTags

Repository files navigation

ICLR 2025 论文和开源项目合集

本仓库旨在收集ICLR最新研究进展，尤其是LLM方面，涉及NLP领域的各个方向，此项目长期不定时更新。
欢迎watch和fork！不过给个star⭐就更好了❤️。
知乎地址：ShuYini
微信公众号: AINLPer（每日更新，欢迎关注）

另外也欢迎大家进入AINLPer星球，每天推送最新、最优质论文，紧跟AIGC大模型前沿进展；另外星球也特设大模型Agent、大模型推理、RAG系统搭建、热门综述、大模型实操、数据集、测试基准、行业发展状况、大厂工作内推等专栏。

感兴趣的小伙伴，赶快扫描下方⬇二维码，新用户加入更有大额优惠券🔖，每年仅需1杯咖啡☕钱！

image-20250303223035800

​ 💎💎💎💎💎💎💎💎💎💎💎💎💎💎

历年ICLR 论文和开源项目合集

Accept Spotlight

1、How new data permeates LLM knowledge and how to dilute it

2、JudgeLM: Fine-tuned Large Language Models are Scalable Judges

3、MQuAKE-Remastered: Multi-Hop Knowledge Editing Can Only Be Advanced with Reliable Evaluations

4、Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws

5、Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence

6、Robustness Reprogramming for Representation Learning

7、LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

8、DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

9、Learning-Augmented Frequent Directions

10、Quality Measures for Dynamic Graph Generative Models

11、Holistically Evaluating the Environmental Impact of Creating Language Models

12、Mixture-of-Agents Enhances Large Language Model Capabilities

13、Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions

14、TopoNets: High performing vision and language models with brain-like topography

15、INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

16、Vision Language Models are In-Context Value Learners

17、Wasserstein Distances, Neuronal Entanglement, and Sparsity

18、WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

19、Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI

20、Multi-session, multi-task neural decoding from distinct cell-types and brain regions

21、Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering

22、AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

23、BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval

24、Online Reinforcement Learning in Non-Stationary Context-Driven Environments

25、CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

26、TabWak: A Watermark for Tabular Diffusion Models

27、Generating Freeform Endoskeletal Robots

28、AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies

29、DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback

30、LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models

31、Exact Certification of (Graph) Neural Networks Against Label Poisoning

32、Test-time Adaptation for Cross-modal Retrieval with Query Shift

33、In Search of Forgotten Domain Generalization

34、TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning

35、Harnessing Diversity for Important Data Selection in Pretraining Large Language Models

36、CausalRivers - Scaling up benchmarking of causal discovery for real-world time-series

37、Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning

38、Progressive Compositionality in Text-to-Image Generative Models

39、Benchmarking Predictive Coding Networks -- Made Simple

40、Can Watermarked LLMs be Identified by Users via Crafted Prompts?

41、On Quantizing Neural Representation for Variable-Rate Video Coding

42、Attention with Markov: A Curious Case of Single-layer Transformers

43、A Second-Order Perspective on Model Compositionality and Incremental Learning

44、Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision

45、EmbedLLM: Learning Compact Representations of Large Language Models

46、Lean-STaR: Learning to Interleave Thinking and Proving

47、NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models

48、DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models

49、Representative Guidance: Diffusion Model Sampling with Coherence

50、Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling

51、InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

52、Revisiting Random Walks for Learning on Graphs

53、DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

54、Control-oriented Clustering of Visual Latent Representation

55、AIR-BENCH 2024: A Safety Benchmark based on Regulation and Policies Specified Risk Categories

56、Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

57、X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

58、Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction

59、Bilinear MLPs enable weight-based mechanistic interpretability

60、Can Large Language Models Understand Symbolic Graphics Programs?

61、AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

62、Advantage-Guided Distillation for Preference Alignment in Small Language Models

63、Simplifying Deep Temporal Difference Learning

64、SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

65、Biologically Constrained Barrel Cortex Model Integrates Whisker Inputs and Replicates Key Brain Network Dynamics

66、Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space

67、The Superposition of Diffusion Models Using the Itô Density Estimator

68、MAGNet: Motif-Agnostic Generation of Molecules from Scaffolds

69、Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

70、IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning

71、RegMix: Data Mixture as Regression for Language Model Pre-training

72、When Attention Sink Emerges in Language Models: An Empirical View

73、PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance

74、Revisiting text-to-image evaluation with Gecko: on metrics, prompts, and human rating

75、Streamlining Redundant Layers to Compress Large Language Models

76、SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints

77、Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach

78、Learning Spatiotemporal Dynamical Systems from Point Process Observations

79、Probabilistic Neural Pruning via Sparsity Evolutionary Fokker-Planck-Kolmogorov Equation

80、Uncovering Gaps in How Humans and LLMs Interpret Subjective Language

81、SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION

82、Demystifying the Token Dynamics of Deep Selective State Space Models

83、Knowledge Localization: Mission Not Accomplished? Enter Query Localization!

84、Realistic Evaluation of Deep Partial-Label Learning Algorithms

85、Graph Sparsification via Mixture of Graphs

86、RAG-SR: Retrieval-Augmented Generation for Neural Symbolic Regression

87、MixEval-X: Any-to-any Evaluations from Real-world Data Mixture

88、DEEM: Diffusion models serve as the eyes of large language models for image perception

89、BodyGen: Advancing Towards Efficient Embodiment Co-Design

90、Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

91、Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

92、Grounding Video Models to Actions through Goal Conditioned Exploration

93、Dense Video Object Captioning from Disjoint Supervision

94、RESuM: A Rare Event Surrogate Model for Physics Detector Design

95、DeLLMa: Decision Making Under Uncertainty with Large Language Models

96、Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation

97、A Periodic Bayesian Flow for Material Generation

98、SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

99、Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEs

100、Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

101、Towards Marginal Fairness Sliced Wasserstein Barycenter

102、Co$^{\mathbf{3}}$Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion

103、Following the Human Thread in Social Navigation

104、OS-ATLAS: Foundation Action Model for Generalist GUI Agents

105、Student-Informed Teacher Training

106、Preference Optimization for Reasoning with Pseudo Feedback

107、OmniRe: Omni Urban Scene Reconstruction

108、Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation

109、Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage

110、Multi-Field Adaptive Retrieval

111、On Disentangled Training for Nonlinear Transform in Learned Image Compression

112、MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

113、ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

114、Towards General-Purpose Model-Free Reinforcement Learning

115、Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

116、Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

117、SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

118、Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

119、Diffusion On Syntax Trees For Program Synthesis

120、Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

121、A CLIP-Powered Framework for Robust and Generalizable Data Selection

122、Fine-tuning with Reserved Majority for Noise Reduction

123、GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation

124、Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation

125、Test-time Alignment of Diffusion Models without Reward Over-optimization

126、ImpScore: A Learnable Metric For Quantifying The Implicitness Level of Sentences

127、LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

128、LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

129、Large-scale and Fine-grained Vision-language Pre-training for Enhanced CT Image Understanding

130、GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks

131、Easing Training Process of Rectified Flow Models Via Lengthening Inter-Path Distance

132、Recovering Manifold Structure Using Ollivier Ricci Curvature

133、AutoCGP: Closed-Loop Concept-Guided Policies from Unlabeled Demonstrations

134、Min-K%++: Improved Baseline for Pre-Training Data Detection from Large Language Models

135、MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

136、Atlas Gaussians Diffusion for 3D Generation

137、Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking

138、Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

139、Programming Refusal with Conditional Activation Steering

140、Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

141、CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

142、ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction

143、D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement

144、Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization

145、Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training

146、DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

147、ThinK: Thinner Key Cache by Query-Driven Pruning

148、4K4DGen: Panoramic 4D Generation at 4K Resolution

149、RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

150、ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks

151、Severing Spurious Correlations with Data Pruning

152、MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion

153、Hymba: A Hybrid-head Architecture for Small Language Models

154、Training-Free Activation Sparsity in Large Language Models

155、Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling

156、CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation

157、Poison-splat: Computation Cost Attack on 3D Gaussian Splatting

158、Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance

159、Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier

160、TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

161、Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data

162、Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

163、LiveBench: A Challenging, Contamination-Limited LLM Benchmark

164、Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion

165、Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model

166、MRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

167、SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks

168、DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo

169、Beyond Next Token Prediction: Patch-Level Training for Large Language Models

170、LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models

171、LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

172、Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation

173、One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

174、MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

175、UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery

176、DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

177、Instance-dependent Early Stopping

178、Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation

179、SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models

Accept Poster

1、Self-supervised contrastive learning performs non-linear system identification

2、Sparse autoencoders reveal selective remapping of visual concepts during adaptation

3、Multi-Label Test-Time Adaptation with Bound Entropy Minimization

4、TabM: Advancing tabular deep learning with parameter-efficient ensembling

5、ToolGen: Unified Tool Retrieval and Calling via Generation

6、Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

7、Video Action Differencing

8、Optimal Transport for Time Series Imputation

9、RaSA: Rank-Sharing Low-Rank Adaptation

10、Offline Model-Based Optimization by Learning to Rank

11、From Search to Sampling: Generative Models for Robust Algorithmic Recourse

12、Monte Carlo Planning with Large Language Model for Text-Based Game Agents

13、Robust Root Cause Diagnosis using In-Distribution Interventions

14、Boosting Neural Combinatorial Optimization for Large-Scale Vehicle Routing Problems

15、SimulPL: Aligning Human Preferences in Simultaneous Machine Translation

16、SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation

17、Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations

18、ADAM: An Embodied Causal Agent in Open-World Environments

19、Beware of Calibration Data for Pruning Large Language Models

20、Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping

21、Herald: A Natural Language Annotated Lean 4 Dataset

22、HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere

23、DPLM-2: A Multimodal Diffusion Protein Language Model

24、Language Imbalance Driven Rewarding for Multilingual Self-improving

25、Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation

26、Distribution-Free Data Uncertainty for Neural Network Regression

27、LASeR: Towards Diversified and Generalizable Robot Design with Large Language Models

28、SOO-Bench: Benchmarks for Evaluating the Stability of Offline Black-Box Optimization

29、Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks

30、Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms

31、Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count

32、One-for-All Few-Shot Anomaly Detection via Instance-Induced Prompt Learning

33、URLOST: Unsupervised Representation Learning without Stationarity or Topology

34、Charting the Design Space of Neural Graph Representations for Subgraph Matching

35、Distilling Dataset into Neural Field

36、SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments

37、SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models

38、Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions

39、GotenNet: Rethinking Efficient 3D Equivariant Graph Neural Networks

40、Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition

41、How to Evaluate Reward Models for RLHF

42、An Efficient Framework for Crediting Data Contributors of Diffusion Models

43、You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning

44、SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration

45、FreDF: Learning to Forecast in the Frequency Domain

46、Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

47、Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

48、Ensembling Diffusion Models via Adaptive Feature Aggregation

49、Model merging with SVD to tie the Knots

50、Making Text Embedders Few-Shot Learners

51、PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph

52、SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

53、Searching for Optimal Solutions with LLMs via Bayesian Optimization

54、Adversarial Generative Flow Network for Solving Vehicle Routing Problems

55、LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement

56、Lawma: The Power of Specialization for Legal Annotation

57、Stiefel Flow Matching for Moment-Constrained Structure Elucidation

58、No Preference Left Behind: Group Distributional Preference Optimization

59、Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis

60、Agent S: An Open Agentic Framework that Uses Computers Like a Human

61、Semi-Parametric Retrieval via Binary Bag-of-Tokens Index

62、PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations

63、Hyperbolic Genome Embeddings

64、RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs

65、Attributing Culture-Conditioned Generations to Pretraining Corpora

66、Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs

67、DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory

68、Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity

69、A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement

70、ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

71、Generalized Behavior Learning from Diverse Demonstrations

72、DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

73、Neural Stochastic Differential Equations for Uncertainty-Aware Offline RL

74、Safety-Prioritizing Curricula for Constrained Reinforcement Learning

75、Towards Federated RLHF with Aggregated Client Preference for LLMs

76、MetaDesigner: Advancing Artistic Typography through AI-Driven, User-Centric, and Multilingual WordArt Synthesis

77、Physics of Language Models: Part 3.2, Knowledge Manipulation

78、On Calibration of LLM-based Guard Models for Reliable Content Moderation

79、Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems

80、Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference

81、Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

82、Agent-Oriented Planning in Multi-Agent Systems

83、Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images

84、Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers

85、ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning

86、STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning

87、Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data

88、Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection

89、Learning Efficient Positional Encodings with Graph Neural Networks

90、Scalable Influence and Fact Tracing for Large Language Model Pretraining

91、Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement

92、Diffusion State-Guided Projected Gradient for Inverse Problems

93、PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS

94、Generating CAD Code with Vision-Language Models for 3D Designs

95、MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization

96、Forgetting Transformer: Softmax Attention with a Forget Gate

97、ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

98、GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

99、Score-based Self-supervised MRI Denoising

100、ProteinBench: A Holistic Evaluation of Protein Foundation Models

101、LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid

102、Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search

103、GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

104、LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

105、Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

106、EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing

107、MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

108、Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

109、What's the Move? Hybrid Imitation Learning via Salient Points

110、LocoVR: Multiuser Indoor Locomotion Dataset in Virtual Reality

111、Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention

112、Conformal Language Model Reasoning with Coherent Factuality

113、Dissecting Adversarial Robustness of Multimodal LM Agents

114、ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration

115、More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed Routing

116、In-context Time Series Predictor

117、Discovering Influential Neuron Path in Vision Transformers

118、Directional Gradient Projection for Robust Fine-Tuning of Foundation Models

119、AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

120、Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing

121、L3Ms — Lagrange Large Language Models

122、ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models

123、Human-inspired Episodic Memory for Infinite Context LLMs

124、ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization

125、Object-Centric Pretraining via Target Encoder Bootstrapping

126、Lossy Compression with Pretrained Diffusion Models

127、Modality-Specialized Synergizers for Interleaved Vision-Language Generalists

128、Self-Normalized Resets for Plasticity in Continual Learning

129、Rapidly Adapting Policies to the Real-World via Simulation-Guided Fine-Tuning

130、CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

131、On Linear Representations and Pretraining Data Frequency in Language Models

132、Quantifying Generalization Complexity for Large Language Models

133、Real2Code: Reconstruct Articulated Objects via Code Generation

134、{$\tau$}-bench: A Benchmark for \underline{T}ool-\underline{A}gent-\underline{U}ser Interaction in Real-World Domains

135、DEPfold: RNA Secondary Structure Prediction as Dependency Parsing.

136、What Matters in Learning from Large-Scale Datasets for Robot Manipulation

137、APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding

138、Differentiable Optimization of Similarity Scores Between Models and Brains

139、Chunk-Distilled Language Modeling

140、GOttack: Universal Adversarial Attacks on Graph Neural Networks via Graph Orbits Learning

141、NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions

142、The Value of Sensory Information to a Robot

143、Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning

144、HelpSteer2-Preference: Complementing Ratings with Preferences

145、Optimizing 4D Gaussians for Dynamic Scene Video from Single Landscape Images

146、Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

147、Palu: KV-Cache Compression with Low-Rank Projection

148、Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity

149、Many-Objective Multi-Solution Transport

150、Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning

151、Learning to Explore and Exploit with GNNs for Unsupervised Combinatorial Optimization

152、InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling

153、Can Knowledge Editing Really Correct Hallucinations?

154、BoneMet: An Open Large-Scale Multi-Modal Murine Dataset for Breast Cancer Bone Metastasis Diagnosis and Prognosis

155、ALLaM: Large Language Models for Arabic and English

156、Improving Graph Neural Networks by Learning Continuous Edge Directions

157、SiReRAG: Indexing Similar and Related Information for Multihop Reasoning

158、Eliciting Human Preferences with Language Models

159、Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework

160、Chemistry-Inspired Diffusion with Non-Differentiable Guidance

161、Aligning Language Models with Demonstrated Feedback

162、Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

163、SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models

164、InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma

165、The Pitfalls of Memorization: When Memorization Hurts Generalization

166、See It from My Perspective: How Language Affects Cultural Bias in Image Understanding

167、Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion

168、Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

169、Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control

170、Cauchy-Schwarz Regularizers

171、HELMET: How to Evaluate Long-context Models Effectively and Thoroughly

172、R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference

173、A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations

174、Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF

175、MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS

176、Procedural Synthesis of Synthesizable Molecules

177、Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning

178、Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?

179、DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

180、Teaching LLMs How to Learn with Contextual Fine-Tuning

181、An Undetectable Watermark for Generative Image Models

182、STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning

183、Residual Stream Analysis with Multi-Layer SAEs

184、Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups

185、Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians

186、On the Transfer of Object-Centric Representation Learning

187、Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement

188、OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination

189、Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks

190、MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

191、Efficient Active Imitation Learning with Random Network Distillation

192、Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation

193、MatExpert: Decomposing Materials Discovery By Mimicking Human Experts

194、Fugatto 1: Foundational Generative Audio Transformer Opus 1

195、Consistency Models Made Easy

196、AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution

197、ElasticTok: Adaptive Tokenization for Image and Video

198、Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models

199、NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

200、Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport

201、Scaling up Masked Diffusion Models on Text

202、Think while You Generate: Discrete Diffusion with Planned Denoising

203、Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

204、Can Transformers Do Enumerative Geometry?

205、EqNIO: Subequivariant Neural Inertial Odometry

206、Interaction Asymmetry: A General Principle for Learning Composable Abstractions

207、Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

208、CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer

209、Provence: efficient and robust context pruning for retrieval-augmented generation

210、CViT: Continuous Vision Transformer for Operator Learning

211、Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment

212、Flow: Modularized Agentic Workflow Automation

213、An Exploration with Entropy Constrained 3D Gaussians for 2D Video Compression

214、Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models

215、Physics-informed Temporal Difference Metric Learning for Robot Motion Planning

216、Scalable Mechanistic Neural Networks

217、One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs

218、E(3)-equivariant models cannot learn chirality: Field-based molecular generation

219、JPEG Inspired Deep Learning

220、The Case for Cleaner Biosignals: High-fidelity Neural Compressor Enables Transfer from Cleaner iEEG to Noisier EEG

221、Tool-Planner: Task Planning with Clusters across Multiple Tools

222、Systematic Relational Reasoning With Epistemic Graph Neural Networks

223、Simple, Good, Fast: Self-Supervised World Models Free of Baggage

224、Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation

225、Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization

226、RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

227、Triples as the Key: Structuring Makes Decomposition and Verification Easier in LLM-based TableQA

228、Agents' Room: Narrative Generation through Multi-step Collaboration

229、Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

230、MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory

231、Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Driving

232、InstantSplamp: Fast and Generalizable Stenography Framework for Generative Gaussian Splatting

233、Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

234、COFlowNet: Conservative Constraints on Flows Enable High-Quality Candidate Generation

235、Multimodal Quantitative Language for Generative Recommendation

236、Monet: Mixture of Monosemantic Experts for Transformers

237、Graph-based Document Structure Analysis

238、Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination

239、3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

240、Redefining the task of Bioactivity Prediction

241、Robust Simulation-Based Inference under Missing Data via Neural Processes

242、Physics-Informed Diffusion Models

243、DynFrs: An Efficient Framework for Machine Unlearning in Random Forest

244、Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

245、Decoupling Layout from Glyph in Online Chinese Handwriting Generation

246、Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

247、ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial Purification

248、Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

249、Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection

250、MA$^2$E: Addressing Partial Observability in Multi-Agent Reinforcement Learning with Masked Auto-Encoder

251、Wayward Concepts In Large Multimodal Models

252、Towards Hierarchical Rectified Flow

253、Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity

254、MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation

255、Do Egocentric Video-Language Models Truly Understand Hand-Object Interactions?

256、The "Law'' of the Unconscious Contrastive Learner: Probabilistic Alignment of Unpaired Modalities

257、System 1.x: Learning to Balance Fast and Slow Planning with Language Models

258、Investigating the Pre-Training Dynamics of In-Context Learning: Task Recognition vs. Task Learning

259、Advancing Graph Generation through Beta Diffusion

260、UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation

261、Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

262、Confidence Elicitation: A New Attack Vector for Large Language Models

263、CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution

264、MCNC: Manifold-Constrained Reparameterization for Neural Compression

265、HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics

266、Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning

267、AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation

268、Forte : Finding Outliers with Representation Typicality Estimation

269、LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

270、NextBestPath: Efficient 3D Mapping of Unseen Environments

271、LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

272、Breaking the Reclustering Barrier in Centroid-based Deep Clustering

273、Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning

274、Frequency-Guided Masking for Enhanced Vision Self-Supervised Learning

275、Generalized Consistency Trajectory Models for Image Manipulation

276、API Pack: A Massive Multi-Programming Language Dataset for API Call Generation

277、Spherical Tree-Sliced Wasserstein Distance

278、Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces

279、Training Robust Ensembles Requires Rethinking Lipschitz Continuity

280、Sparse Autoencoders Do Not Find Canonical Units of Analysis

281、MUSE: Machine Unlearning Six-Way Evaluation for Language Models

282、Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport

283、Small Models are LLM Knowledge Triggers for Medical Tabular Prediction

284、PQMass: Probabilistic Assessment of the Quality of Generative Models using Probability Mass Estimation

285、Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks

286、BANGS: Game-theoretic Node Selection for Graph Self-Training

287、UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate

288、Generating Likely Counterfactuals Using Sum-Product Networks

289、Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization

290、PooDLe🐩: Pooled and dense self-supervised learning from naturalistic videos

291、TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation

292、CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

293、TD-Paint: Faster Diffusion Inpainting Through Time Aware Pixel Conditioning

294、Number Cookbook: Number Understanding of Language Models and How to Improve It

295、Bringing NeRFs to the Latent Space: Inverse Graphics Autoencoder

296、Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

297、Factor Graph-based Interpretable Neural Networks

298、Alchemy: Amplifying Theorem-Proving Capability Through Symbolic Mutation

299、Agent Skill Acquisition for Large Language Models via CycleQD

300、KBLaM: Knowledge Base augmented Language Model

301、MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks

302、An Information Criterion for Controlled Disentanglement of Multimodal Data

303、ReAttention: Training-Free Infinite Context with Finite Attention Scope

304、SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

305、Periodic Materials Generation using Text-Guided Joint Diffusion Model

306、QERA: an Analytical Framework for Quantization Error Reconstruction

307、Efficient Discovery of Pareto Front for Multi-Objective Reinforcement Learning

308、Semi-Supervised CLIP Adaptation by Enforcing Semantic and Trapezoidal Consistency

309、Unsupervised Zero-Shot Reinforcement Learning via Dual-Value Forward-Backward Representation

310、Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

311、Biologically Plausible Brain Graph Transformer

312、Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving

313、UV-Attack: Physical-World Adversarial Attacks on Person Detection via Dynamic-NeRF-based UV Mapping

314、Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization

315、Optimistic Games for Combinatorial Bayesian Optimization with Application to Protein Design

316、DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation

317、Vision and Language Synergy for Rehearsal Free Continual Learning

318、Rethinking Multiple-Instance Learning From Feature Space to Probability Space

319、Why Does the Effective Context Length of LLMs Fall Short?

320、Complementary Label Learning with Positive Label Guessing and Negative Label Enhancement

321、Training-free LLM-generated Text Detection by Mining Token Probability Sequences

322、Dataset Ownership Verification in Contrastive Pre-trained Models

323、MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

324、Standardizing Structural Causal Models

325、OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

326、VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

327、Bootstrapping Language Models with DPO Implicit Rewards

328、Learning system dynamics without forgetting

329、Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs

330、SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

331、SysBench: Can LLMs Follow System Message?

332、Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation

333、AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning

334、OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces

335、Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics

336、Equivariant Neural Functional Networks for Transformers

337、Weighted-Reward Preference Optimization for Implicit Model Fusion

338、Locality-aware Gaussian Compression for Fast and High-quality Rendering

339、A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation

340、NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields

341、InstaRevive: One-Step Image Enhancement via Dynamic Score Matching

342、A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations

343、Unsupervised Multiple Kernel Learning for Graphs via Ordinality Preservation

344、MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

345、Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs

346、Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective

347、On the Performance Analysis of Momentum Method: A Frequency Domain Perspective

348、Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

349、Jamba: Hybrid Transformer-Mamba Language Models

350、Learning 3D Perception from Others' Predictions

351、Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View

352、Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On

353、Universal Image Restoration Pre-training via Degradation Classification

354、ConMix: Contrastive Mixup at Representation Level for Long-tailed Deep Clustering

355、ADePT: Adaptive Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

356、Designing Concise ConvNets with Columnar Stages

357、Taming Overconfidence in LLMs: Reward Calibration in RLHF

358、Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

359、StringLLM: Understanding the String Processing Capability of Large Language Models

360、Consistent Flow Distillation for Text-to-3D Generation

361、A Benchmark for Semantic Sensitive Information in LLMs Outputs

362、xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

363、From Commands to Prompts: LLM-based Semantic File System for AIOS

364、SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios

365、Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs

366、BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics

367、BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

368、HERO: Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning

369、Fully-inductive Node Classification on Arbitrary Graphs

370、Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

371、Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length

372、Detecting Backdoor Samples in Contrastive Language Image Pretraining

373、Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generation

374、Competing Large Language Models in Multi-Agent Gaming Environments

375、Reinforcement learning with combinatorial actions for coupled restless bandits

376、OGBench: Benchmarking Offline Goal-Conditioned RL

377、CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion

378、Aligned LLMs Are Not Aligned Browser Agents

379、Edge Prompt Tuning for Graph Neural Networks

380、Optimized Multi-Token Joint Decoding With Auxiliary Model for LLM Inference

381、Algorithmic Stability Based Generalization Bounds for Adversarial Training

382、Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods

383、MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

384、AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning

385、Zero-shot Model-based Reinforcement Learning using Large Language Models

386、Interpreting the Second-Order Effects of Neurons in CLIP

387、GOAL: A Generalist Combinatorial Optimization Agent Learner

388、Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

389、Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

390、Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification

391、Improved Training Technique for Latent Consistency Models

392、Dynamic Negative Guidance of Diffusion Models

393、Adversarial Training for Defense Against Label Poisoning Attacks

394、Trajectory attention for fine-grained video motion control

395、Diff-Prompt: Diffusion-driven Prompt Generator with Mask Supervision

396、LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

397、Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization

398、HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

399、A General Framework for Producing Interpretable Semantic Text Embeddings

400、Multimodal Situational Safety

401、Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning

402、Trusted Multi-View Classification via Evolutionary Multi-View Fusion

403、HQGS: High-Quality Novel View Synthesis with Gaussian Splatting in Degraded Scenes

404、REFINE: Inversion-Free Backdoor Defense via Model Reprogramming

405、Tight Clusters Make Specialized Experts

406、Real-Time Video Generation with Pyramid Attention Broadcast

407、Large Convolutional Model Tuning via Filter Subspace

408、Spectro-Riemannian Graph Neural Networks

409、Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

410、Subtask-Aware Visual Reward Learning from Segmented Demonstrations

411、TopoDiffusionNet: A Topology-aware Diffusion Model

412、3DGS-Drag: Dragging Gaussians for Intuitive Point-Based 3D Editing

413、Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation

414、What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?

415、Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings

416、Simulating Human-like Daily Activities with Desire-driven Autonomy

417、CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation

418、ParaSolver: A Hierarchical Parallel Integral Solver for Diffusion Models

419、Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models

420、RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards

421、GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

422、Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization

423、Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs

424、AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data

425、DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

426、Unbounded: A Generative Infinite Game of Character Life Simulation

427、Metric-Driven Attributions for Vision Transformers

428、Diffusion Models Are Real-Time Game Engines

429、Going Beyond Feature Similarity: Effective Dataset distillation based on Class-aware Conditional Mutual Information

430、GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation

431、DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving

432、N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning

433、Rethinking Light Decoder-based Solvers for Vehicle Routing Problems

434、Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior

435、Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness

436、Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation

437、SpinQuant: LLM Quantization with Learned Rotations

438、On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models

439、Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?

440、A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language

441、Adaptive Retention & Correction: Test-Time Training for Continual Learning

442、Do WGANs succeed because they minimize the Wasserstein Distance? Lessons from Discrete Generators

443、Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection

444、Correlating instruction-tuning (in multimodal models) with vision-language processing (in the brain)

445、WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling

446、Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning

447、Enhancing Multilingual Reasoning in LLMs: Insights from Cross-Linguistic Correlations and Optimal Data Proportions

448、PhysPDE: Rethinking PDE Discovery and a Physical HYpothesis Selection Benchmark

449、Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

450、Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

451、Improving Data Efficiency via Curating LLM-Driven Rating Systems

452、VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning

453、ECHOPulse: ECG Controlled Echocardio-gram Video Generation

454、A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals

455、Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment

456、Causal Graph Transformer for Treatment Effect Estimation Under Unknown Interference

457、Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion

458、Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning

459、Learning Gain Map for Inverse Tone Mapping

460、Latent Radiance Fields with 3D-aware 2D Representations

461、Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling

462、SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision

463、Long-Sequence Recommendation Models Need Decoupled Embeddings

464、TIPS: Text-Image Pretraining with Spatial awareness

465、OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code

466、Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems

467、Halton Scheduler for Masked Generative Image Transformer

468、MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow

469、Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition

470、Framer: Interactive Frame Interpolation

471、GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting

472、BrainUICL: An Unsupervised Individual Continual Learning Framework for EEG Applications

473、Is In-Context Learning Sufficient for Instruction Following in LLMs?

474、Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

475、Learning Evolving Tools for Large Language Models

476、Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning

477、OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer

478、BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL

479、RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

480、VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

481、GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting

482、Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision Models

483、PAL: Sample-Efficient Personalized Reward Modeling for Pluralistic Alignment

484、Dynamic Diffusion Transformer

485、McEval: Massively Multilingual Code Evaluation

486、SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

487、Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling

488、Improving Language Model Distillation through Hidden State Matching

489、Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence

490、Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

491、Revisiting Convolution Architecture in the Realm of DNA Foundation Models

492、Episodic Novelty Through Temporal Distance

493、Scaling Autonomous Agents via Automatic Reward Modeling And Planning

494、FlickerFusion: Intra-trajectory Domain Generalizing Multi-agent Reinforcement Learning

495、Gradient-Free Generation for Hard-Constrained Systems

496、M^3PC: Test-time Model Predictive Control using Pretrained Masked Trajectory Model

497、Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models

498、ProtoSnap: Prototype Alignment For Cuneiform Signs

499、DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation

500、Learning Spatial-Semantic Features for Robust Video Object Segmentation

501、Toward Generalizing Visual Brain Decoding to Unseen Subjects

502、On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning

503、Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing

504、PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection

505、Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model

506、MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors

507、VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning

508、SAGEPhos: Sage Bio-Coupled and Augmented Fusion for Phosphorylation Site Detection

509、Training-Free Dataset Pruning for Instance Segmentation

510、PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify

511、ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICY

512、Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision

513、Locality Sensitive Avatars From Video

514、Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

515、LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning

516、PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

517、Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment

518、AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

519、COME: Test-time Adaption by Conservatively Minimizing Entropy

520、Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

521、CoInD: Enabling Logical Compositions in Diffusion Models

522、Automated Design of Agentic Systems

523、ParetoFlow: Guided Flows in Multi-Objective Optimization

524、Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It

525、Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

526、A Coefficient Makes SVRG Effective

527、FaceShot: Bring Any Character into Life

528、Do Deep Neural Network Solutions Form a Star Domain?

529、FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

530、Revisiting In-context Learning Inference Circuit in Large Language Models

531、VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing

532、COMBO: Compositional World Models for Embodied Multi-Agent Cooperation

533、FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

534、Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

535、SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

536、Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention

537、Gated Delta Networks: Improving Mamba2 with Delta Rule

538、3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

539、Understanding and Enhancing the Transferability of Jailbreaking Attacks

540、AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction

Accept Oral

1、RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

2、TopoLM: brain-like spatio-functional organization in a topographic language model

3、Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows

4、Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

5、Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition

6、Learning to Search from Demonstration Sequences

7、Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

8、MAP: Multi-Human-Value Alignment Palette

9、Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment

10、Learning to Discover Regulatory Elements for Gene Expression Prediction

11、Brain Bandit: A Biologically Grounded Neural Network for Efficient Control of Exploration

12、Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

13、Progressive Compression with Universally Quantized Diffusion Models

14、Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization

15、Instant Policy: In-Context Imitation Learning via Graph Diffusion

16、RB-Modulation: Training-Free Stylization using Reference-Based Modulation

17、Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

18、Oscillatory State-Space Models

19、Attention as a Hypernetwork

20、Energy-based Backdoor Defense Against Federated Graph Learning

21、Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

22、RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

23、Residual Deep Gaussian Processes on Manifolds

24、Learning to Discretize Denoising Diffusion ODEs

25、Proteina: Scaling Flow-based Protein Structure Generative Models

26、Feedback Favors the Generalization of Neural ODEs

27、Scaling and evaluating sparse autoencoders

28、Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

29、TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

30、Copyright-Protected Language Generation via Adaptive Model Fusion

31、BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

32、Rethinking Reward Modeling in Preference-based Large Language Model Alignment

33、Progressive distillation induces an implicit curriculum

34、miniCTX: Neural Theorem Proving with (Long-)Contexts

35、Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

36、Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation

37、Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

38、MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions

39、On Scaling Up 3D Gaussian Splatting Training

40、BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

41、SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning

42、Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching

43、PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration

44、A Probabilistic Perspective on Unlearning and Alignment for Large Language Models

45、MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

46、Subgraph Federated Learning for Local Generalization

47、Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series

48、Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates

49、Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File Selection

50、SymmetricDiffusers: Learning Discrete Diffusion Models over Finite Symmetric Groups

51、Data Scaling Laws in Imitation Learning for Robotic Manipulation

52、Population Transformer: Learning Population-level Representations of Neural Activity

53、HiRA: Parameter-Efficient Hadamard High-Rank Adaptation for Large Language Models

54、On Conformal Isometry of Grid Cells: Learning Distance-Preserving Position Embedding

55、How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning

56、A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules

57、MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

58、LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior

59、Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

60、EmbodiedSAM: Online Segment Any 3D Thing in Real Time

61、Robustness Inspired Graph Backdoor Defense

62、Proxy Denoising for Source-Free Domain Adaptation

63、Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

64、On the Identification of Temporal Causal Representation with Instantaneous Dependence

65、WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

66、Learning Dynamics of LLM Finetuning

67、More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

68、Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

69、Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

70、ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids

71、MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

72、Compositional Entailment Learning for Hyperbolic Vision-Language Models

73、DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL

74、Composing Unbalanced Flows for Flexible Docking and Relaxation

75、On the Role of Attention Heads in Large Language Model Safety

76、AlphaEdit: Null-Space Constrained Model Editing for Language Models

77、Prioritized Generative Replay

78、Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport

79、No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

80、The Geometry of Categorical and Hierarchical Concepts in Large Language Models

81、Variational Diffusion Posterior Sampling with Midpoint Guidance

82、Retrieval Head Mechanistically Explains Long-Context Factuality

83、NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields

84、Differential Transformer

85、High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation

86、Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

87、REEF: Representation Encoding Fingerprints for Large Language Models

88、Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free

89、Data Selection via Optimal Control for Language Models

90、GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling

91、LLM-SR: Scientific Equation Discovery via Programming with Large Language Models

92、Rethinking the generalization of drug target affinity prediction algorithms via similarity aware evaluation

93、LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

94、Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning

95、Cut Your Losses in Large-Vocabulary Language Models

96、Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models

97、FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

98、SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers

99、REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments

100、MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

101、Do as We Do, Not as You Think: the Conformity of Large Language Models

102、Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

103、Probabilistic Learning to Defer: Handling Missing Expert Annotations and Controlling Workload Distribution

104、Artificial Kuramoto Oscillatory Neurons

105、ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding

106、A Decade's Battle on Dataset Bias: Are We There Yet?

107、Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding

108、Open-World Reinforcement Learning over Long Short-Term Imagination

109、SAM 2: Segment Anything in Images and Videos

110、Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference under Ambiguities

111、A Computational Framework for Modeling Emergence of Color Vision in the Human Brain

Accept conditionaloral

1、Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

2、TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation

3、Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency

4、CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation

5、PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Accept conditionalspotlight

1、OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

2、FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs

Accept conditionalposter

1、Scaling Speech-Text Pre-training with Synthetic Interleaved Data

2、K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language Models

3、DiscoveryBench: Towards Data-Driven Discovery with Large Language Models

4、Image Watermarks are Removable using Controllable Regeneration from Clean Noise

5、ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

6、Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks

7、SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

8、Interpretable Compressed Descriptions For Image Generation

9、Measuring And Improving Engagement of Text-to-Image Generation Models

10、AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

11、Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning

12、TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models

13、Diversity-Rewarded CFG Distillation

14、GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

15、Looking Backward: Streaming Video-to-Video Translation with Feature Banks

16、Personalized Representation from Personalized Generation

17、VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

18、Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models

19、$F^3Set$: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos

20、SWEb: A Large Web Dataset for the Scandinavian Languages

21、Unleashing the Potential of Vision-Language Pre-Training for 3D Zero-Shot Lesion Segmentation via Mask-Attribute Alignment

22、PersonalLLM: Tailoring LLMs to Individual Preferences

23、BadRobot: Jailbreaking Embodied LLMs in the Physical World

24、Grounding Multimodal Large Language Model in GUI World

25、Personalized Visual Instruction Tuning

26、TaskGalaxy: Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types

27、TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident

28、Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels

29、UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation

30、DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors

31、Aria-MIDI: A Dataset of Piano MIDI Files for Symbolic Music Modeling

32、Depth Any Video with Scalable Synthetic Data

33、HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

34、SONICS: Synthetic Or Not - Identifying Counterfeit Songs

35、CycleResearcher: Improving Automated Research via Automated Review

36、Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

About

历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.

Topics

python machine-learning transformer gpt nlp-machine-learning nlp-keywords-extraction iclr2021 paperwithcode iclr2022 llms iclr2023 llm-agent llm-training gemmini llm-framework iclr2024 llm-reasoning llama3 deep-learning-paper

Resources

Readme
Activity

Stars

178 stars

Watchers

4 watching

Forks

9 forks
Report repository

Releases

No releases published

Packages

No packages published