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
Learning Human-Robot Collaboration via Heterogeneous-Agent Lyapunov Policy Optimization
Learning in Bayesian Stackelberg Games With Unknown Follower's Types
Learning in Structured Stackelberg Games
Learning Interpretable Options by Identifying Reward Diffusion Bottlenecks in Reinforcement Learning
Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning
Learning Junta Distributions, Quantum Junta States, and QAC$^0$ Circuits
Learning Latent Action World Models in the Wild
Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels
Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models
Learning Manifold and Itô Dynamics with Branched Neural Rough Differential Equations
Learning Manifold Data with Flow Matching
Learning Molecular Semantic Invariant Representation with Prototype Constraint
Learning More from Less: Unlocking Internal Representations for Benchmark Compression
Learning Multi-Agent Coordination via Sheaf-ADMM
Learning Multi-Scale Hypergraph for High-Order Brain Connectivity Analysis
Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning
Learning Normalized Energy Models for Linear Inverse Problems
Learning Partial Concept Classes and Universal Rates Under Massart Noise
Learning Permutation Distributions via Reflected Diffusion on Ranks
Learning Permutation from Structure Without Supervision
Learning Permutation-invariant Macroscopic Dynamics
Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
Learning Randomized Reductions
Learning Rate Annealing Improves Tuning Robustness in Stochastic Optimization
Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
Learning Reward–Cost Balance in Safe RL via Score-Based World Models
Learning Rewrite-Invariant Reasoning with Targeted Alternation Training
Learning Robust Multi-Agent Policies via Selective Adversarial Fault Induction
Learning Self-Correction in Vision–Language Models via Rollout Augmentation
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm
Learning Sparse Visual Representations via Spatial-Semantic Factorization
Learning Stochastic Bridges for Video Object Removal via Video-to-Video Translation
Learning Structured Reasoning via Tractable Trajectory Control
Learning syntax without semantics: Disentangled tiny language models
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models
Learning the Best Under Constraints: A Duality-Based Framework
Learning the ESG Geometry with Domain Aware Language Models
Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approach
Learning the Minimum Action Distance
Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
Learning Tight Rejection Boundaries without Negatives for Strict One-Class Audio Deepfake Detection
Learning to Approximate Uniform Facility Location via Graph Neural Networks
Learning to Bet for Horizon-Aware Anytime-Valid Testing
Learning to Correct: Reinforcement Learning for Multi-Attempt Chain-of-Thought
Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
Learning to Discover at Test Time
Learning to Emulate Chaos: Adversarial Optimal Transport Regularization

« prev Page 63/130 next »