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
Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability
Evaluating and Steering Modality Preferences in Multi-modal LLMs
Evaluating Bivariate Causal Statements Based on Mutual Compatibility
Evaluating Contextual Illegality: AI Compliance in Corporate Law Scenarios
Evaluating Language Models in Realistic Conversational Contexts
Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
Evaluating LLM Uncertainty in Long-Form Generation Using Deterministic Ground Truth
Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems
Evaluating Object-Centric Models beyond Object Discovery
Evaluating Parameter Efficient Methods for RLVR
Evaluating Relational Reasoning in LLMs with REL
Evaluating Robustness of Reasoning Models on Parameterized Logical Problems
Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
Even Faster Kernel Matrix Linear Algebra via Density Estimation
Event2Vec: Processing neuromorphic events directly by representations in vector space
Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs
Evidential Copula Concept Embedding Models
Evidential Reasoning Advances Interpretable Real-World Disease Screening
EVMbench: Evaluating AI Agents on Smart Contract Security
EvoC2F: Compiling Tool Orchestration for Efficient and Evolvable LLM Agents
EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
EvoClaw: Evaluating AI Agents on Continuous Software Evolution
EvoEGF-Mol: Evolving Exponential Geodesic Flow for Structure-based Drug Design
EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
Evolution of Benchmark: Black-Box Optimization Benchmark Design through Large Language Model
Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
Evolution Strategies at the Hyperscale
Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization
Evolving Interpretable Constitutions for Multi-Agent Coordination
Evolving Quantitative Reasoning through Self-Play in Digital Twin Markets
EVOLVING ROLLOUTS: Harnessing Historical Experience for Web Agent Evolution in Reinforcement Learning
EvoMAS: Evolutionary Generation of Multi-Agent Systems
EvoMAS: Heuristics in the Loop—Evolving Smarter Agentic Workflows
EvReflection: Event-Driven Micro-Dynamics for Reflection Removal
Exact and Approximate Algorithms for Polytree Learning
Exact Functional ANOVA Decomposition for Categorical Inputs Models
Exactly Computing do-Shapley Values
Exact Unlearning in Reinforcement Learning
Excited Pfaffians: Generalized Neural Wave Functions Across Structure and State
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
Executable Agentic Memory for GUI Agent
ExpAlign: Expectation-Guided Vision–Language Alignment for Open-Vocabulary Grounding
Expandable, Compressible, Mineable: Open-World Thermal Image Restoration
Expandable, Compressible, Mineable: Open-World Thermal Infrared Image Restoration
Expanding the AI Evaluation Toolbox with Statistical Models
Expanding the Capabilities of Reinforcement Learning via Text Feedback
Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations
Expand Neurons, Not Parameters
Expectation Alignment of Language Models for Real-World User Expectations

« prev Page 39/130 next »