ICML 2026

6,487 papers

Top Research Directions

Research directions most represented by ICML 2026 papers.

Scaling Language Model Reasoning Beyond Verifiable Rewards 79
Group Relative Policy Optimization for Large Reasoning Models 63
General Purpose Reasoning from Specialized Reinforcement Learning 62
Overcoming the Iterative Inference Latency of Diffusion Models 50
Shifting from Static Benchmarks to Dynamic Evaluation 47
Controlling Language Models Through Latent Space Interventions 45
Resolving Superposition with Sparse Autoencoders 42
Autonomous Code Refinement via Execution Feedback Loops 41
The Performance Cliff in Ultra Low Bit Quantization 41
Activation Steering for Inference Time Model Control 39
Mitigating Expert Collapse in Sparse Mixture of Experts 37
Proxy Objective Exploitation in Language Model Alignment 37
The Decoupling of Visual Perception and Logical Reasoning 36
Mitigating Computational Overthinking in Large Reasoning Models 35
Input Adaptive Compute Allocation for Language Models 33

Top Authors

AuthorPapers
Junchi Yan19
Min Zhang19
Tat-Seng Chua15
Haoxuan Li14
Philip Torr14
Yong Li14
Kun Zhang13
Li Shen13
Tianlong Chen13
Xiang Wang13
Xin Geng13
Yejin Choi13
Bo An12
Mihaela van der Schaar12
Xunliang Cai12
Bo Han11
Ge Zhang11
Han Liu11
Jiang Bian11
LEI BAI11

Impactful Papers

Papers from ICML 2026 that shaped research clusters.

Foundational

Papers

Title
VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding
VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
VideoMAETok: Boosting Video Diffusion Models via Masked Autoencoders as Tokenizers
Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
VideoSEAL: Mitigating Evidence Misalignment in Agentic Long Video Understanding by Decoupling Answer Authority
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
Video-SVD: Efficient Video Diffusion via Orthogonal Basis Composition
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
VideoTrace-R1: Long Video-based Retrieval-Augmented Generation via Reinforcement Learning
VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning
VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding
ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models
View Space: Learning Representation across Arbitrary Graphs
VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning
VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
Vision-aligned Latent Reasoning for Multi-modal Large Language Model
Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models
Vision-Language-Action Pretraining from Large-Scale Human Videos
Vision Language Models Cannot Reason About Physical Transformation
VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning
Vision Transformer Finetuning Benefits from Non-Smooth Components
Visual Implicit Autoregressive Modeling
Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
Visual Persuasion: What Influences Decisions of Vision-Language Models?
VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge
VisualScore: Learning Holistic Visual Quality Scores via Multi-Task Reasoning
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ViTok-v2: Scaling Native Resolution Autoencoders to 5 Billion Parameters
VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos
VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models
VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
VLANeXt: Recipes for Building Strong VLA Models
VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing
V-LynX: Token Interface Alignment for Video+X LLMs
VocSim A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio
Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction
VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection
VR-Thinker: Boosting Multimodal Reward Models through Think with Image Reasoning
VR-Thinker: Boosting Video Reward Models through Think-with-Image Reasoning
VSCD: Video-based Scene Change Detection in Unaligned Scenes
VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning

« prev Page 126/130 next »