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
ReaForest: Fostering Generative Video Reasoning for Spatial Planning
Real Data Lies: Unveiling and Closing the Quality Shortcut in Generalizable AI-Generated Video Detection
RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
Realizable Bayes-Consistency for General Metric Losses
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment
Real-Time Aligned Reward Model beyond Semantics
Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
RealtimeTool: Parallel Decoding for Real-Time LLM Function Calling
Real-Time Visual Attribution Streaming in Thinking Model
Real-World Unsupervised Models Generalize to Predict Brain Responses to Out-of-Distribution Stimuli
REAR: Test-time Preference Realignment through Reward Decomposition
ReasonEdit: Editing Vision--Language Models using Human Reasoning
Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
Reasoning Can Be Restored by Correcting a Few Decision Tokens
Reasoning Compartmentalization: Bridging the Concretization Gap via Abstraction-based Routing
Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
Reasoning Models Are Test Exploiters: Rethinking Multiple Choice
Reasoning Models Struggle to Control their Chains of Thought
Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
Reasoning Phases Are Continuous, Not Discrete: Evidence from Switching Linear Dynamical Systems Applied to Chain-of-Thought Residual Streams
Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
Reasoning Quality Emerges Early: Data Curation for Reasoning Models
Reasoning Structure of Large Language Models
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning
Reasoning-VLA: An Efficient and Spatial-Guided General Vision-Language-Action Reasoning Model for Autonomous Driving
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
Reason with Thumbnails, Answer with Focus: An Efficient and Effective Paradigm for Multimodal Grounded Visual Reasoning
ReAugment: Targeted Few-Shot Time Series Augmentation via Model Zoo-Guided Reinforcement Learning
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems
ReCoG: Relational and Compact Context Graph Learning for Few-shot Molecular Property Prediction
Reconstructing Template-Memorized Images from Natural Prompts
Reconstruction Outcomes Look Similar but Processes Differ: Improving Context Consistency and Coverage in Graph Masked Auto-Encoder
Recontextualization Mitigates Specification Gaming Without Modifying the Specification
Recovering Hidden Reward in Diffusion-Based Policies
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
RECOVER: Reliable Detection of Unauthorized Data Usage in Text-to-Image Diffusion Models via Inversion Robustness
Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations
RECTOR: Masked Region-Channel-Temporal Modeling for Affective and Cognitive Representation Learning
Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
Recurrent Structural Policy Gradient for Partially Observable Mean Field Games
Recursive Binding on a Budget: Subspace Carving in Order-$p$ Tensor Memories
Recursive Models for Long-Horizon Reasoning

« prev Page 92/130 next »