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
How Hard Is Science?
How High is ‘High’? Rethinking the Roles of Dimensionality in Topological Data Analysis and Manifold Learning
How Language Models Process Negation
How Many Different Outputs Can a Transformer Generate?
How much can language models memorize?
How (Not) to Hybridize Neural and Mechanistic Models for Epidemiological Forecasting
How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability
How Powerful are LLMs in Generating Formal Program Specifications?
How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess
How RLHF Amplifies Sycophancy
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
How Should Transformers Encode Numeric Values in Electronic Health Records?
How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs
How to Correctly Report LLM-as-a-Judge Evaluations
How to Fine-Tune a Reasoning Model? A Teacher–Student Cooperation Framework to Synthesize Student-Consistent SFT Data
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
How to Price Data: A Market Equilibrium Based Approach
How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
How Transformers Represent Hierarchies: A Local-to-Global Mechanism
HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement Learning
HSGG: Training-Free Hierarchical Scene Graph Generation with Geometry-Guided Relation Reasoning
HSMAD: Heterophily-Driven Spectral and Manifold Learning for Graph Anomaly Detection
HTAC: Hierarchical Task-Aware Composition for Continual Offline Reinforcement Learning
Hugging Carbon: Quantifying the Training Carbon Emissions of AI Models at Scale
Human-AI Collaborative Uncertainty Quantification
Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning
HumanLM: Simulating Users with State Alignment Beats Response Imitation
Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models
HVAE: Hyperbolic Variational Autoencoder For Flexible Knowledge Transfer Across Multiple Domains
HVR-Met: A Hypothesis-Verification-Replanning Agentic System for Extreme Weather Diagnosis
HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference
Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
HybridOM: Hybrid Physics-Based and Data-Driven Global Ocean Modeling with Efficient Regional Downscaling
HybridOM: Hybrid Physics-Based and Data-Driven Global Ocean Modeling with Efficient Spatial Downscaling
Hybrid Policy Distillation for LLMs
Hybrid Reinforcement Learning in Adversarial Markov Decision Processes
Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning
HyMTRL: A Hybrid Multi-Task Reinforcement Learning Framework via Phased Policy Evolution
HypCL: Adapting CLIP in Hyperbolic Space for Continual Learning
Hyperbolic Associative Memory Networks
Hyperbolic Hierarchical Alignment for Video-Based Visible-Infrared Person Re-Identification
Hyperbolic Multimodal Continual Learning
Hyperbolic Neural Operator
Hyperbolic neural population geometry benefits computation
Hyperbolic RQ-VAE enhanced Generative Recommendation with Differential-Length Codebook Strategy
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning
Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning
HyperMLP: An Integrated Perspective for Sequence Modeling
Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks

« prev Page 54/130 next »