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
Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noises
LipoPU: Pocket-level Prediction of Lipid-Protein Interactions via Positive-Unlabeled Learning
Listening Through the Noise: Cauchy-Driven Diffusion Bridges for Robust Gastrointestinal Auscultation and Clinical Benchmarking
LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution
LithoDreamer: A Physics-Informed World Model for Multi-Stage Computational Lithography
LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
LitReview Arena: Evaluating Literature Review Agents with Battle-style Peer Review Platform
LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment
Little By Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention
LiveFigure: Generating Editable Scientific Illustration with VLM Agents
LIVE: Long-horizon Interactive Video World Modeling
LiveNewsBench: Evaluating Web Search Agents with Freshly Curated News
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation
LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
LLM-Guided Diagnostic Evidence Alignment for Medical Vision–Language Pretraining under Limited Pairing
LLM-Guided Loop Bound Generation for Program Termination Verification
LLMInertia: Adaptive Counter-Inertial Reasoning to Improve Evidence Faithfulness in Large Language Models
LLM-MatLogic: Executable Exchange Contracts for Knowledge-Graph Query Answering with Scoped Negation
LLM Priors for ERM over Programs
LLMs as Noisy Channels: A Shannon Perspective on Model Capacity and Scaling Laws
LLM Self-Recognition: Steering and Retrieving Activation Signatures
LLMs Lean on Priors, Not Programming Language Semantics
LLMs with in-context learning for Algorithmic Theoretical Physics
LLM Watermark Evasion via Bias Inversion
LMCleaner: Efficient and Certified Online Unlearning via Influence Propagation Truncation
LMM4-IC4K: A Large Multimodal Model Powered Integrated Circuit Footprint Geometry Understanding
LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate Descent
LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth
Local Constrained Bayesian Optimization
Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
Localize and Neutralize: Gradient-Guided Token Suppression Against Visual Prompt Injection Attack
Localized, High-resolution Geographic Representations with Slepian Functions
Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Locally Coherent Parallel Decoding in Diffusion Language Models
Local MAP Sampling for Diffusion Models
Local Mechanisms of Compositional Generalization in Conditional Diffusion
Local Minima in Quadratic-Penalty Relaxations of Binary Linear Programs
Local-Minima-Preserving Polynomial Relaxation of Ising Problems
Local Policies for Graph-Structured Markov Decision Processes
Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization
Locate then Correct: Debiasing Attention Heads in CLIP

« prev Page 66/130 next »