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
MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
Matrix-Free GPU Semidefinite Programming for Quantum Ordered Search at the k=6 Frontier
Matroid Algorithms Under Size-Sensitive Independence Oracles
MAVRL: Learning Reward Functions from Multiple Feedback Types with Amortized Variational Inference
Maximin Relative Improvement: Fair Learning as a Bargaining Problem
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
Maximum-Likelihood Learning of Latent Dynamics Without Reconstruction
Maximum Likelihood Reinforcement Learning
MaxSAT-Based Compression for Tsetlin Machines
MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning
MC-HNN: Learning Latent Structural Semantics and High-Rank Representations for Hypergraph Neural Networks
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
MDGMIX: Boundary-Aware Subgraph Mixing for Multi-Domain Graph Pre-Training
MDN: Parallelizing Stepwise Momentum for Delta Linear Attention
MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models
Mean Flow Policy Optimization
Mean-Shift PCA by Knockoff Mean
Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers
Measuring Agents in Production
Measuring and Mitigating Post-Hoc Rationalization in Reverse Chain-of-Thought Generation
Measuring Intent Comprehension in LLMs
Measuring Meta-Cultural Competency: A Spectral Framework for LLM Knowledge Structures
MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
Mechanisms of Introspective Awareness
Mechanistic Anomaly Detection via Functional Attribution
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding
MEC: Machine-Learning-Assisted Generalized Entropy Calibration for Semi-Supervised Mean Estimation
MEDA: Medical-Oriented Activation Editing for Hallucination Mitigation in Medical Large Vision-Language Model
MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation
MedCRP-CL: Continual Medical Image Segmentation via Bayesian Nonparametric Semantic Modality Discovery
MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts
MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling
Med-Scout: Curing MLLMs' Geometric Blindness in Medical Perception via Geometry-Aware RL Post-Training
Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation
MedSIGHT: Towards Grounded Visual Comprehension in Medical Large Vision-Language Models
MEDUSA: Motion Elimination in Diffusion Using Spectral Attack
Meerkat-VL: Implicit Risk Safety Alignment in Multimodal LLMs via Perceptual Reasoning and Self-Verification
MEG-XL: Data-Efficient Brain-to-Text via Long-Context Pre-Training
Membership Inference Attacks for Unseen Classes
MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning
MemEvolve: Meta-Evolution of Agent Memory Systems
MemIncept: Steering LLM Agents via Cooperative Stealthy Memory Injections
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

« prev Page 69/130 next »