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
Graph Neural Dynamics via Learned Energy and Tangential Flows
Graph Neural Networks Are Not Continuous Across Graph Resolutions
Graph of States: Solving Abductive Tasks with Large Language Models
GraphP-FL: Personalized Federated Graph Learning via Dynamic Structure Awareness and Fisher Information Elastic Alignment
GraphPFN: A Prior-Data Fitted Graph Foundation Model
Graph-Preference Learning: Debiasing Network-Sampled Human Feedback for Target Welfare Estimation
Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning
Graph Rewiring based on Flow Alignment for Improving Fluid Simulation
GRASP: Awakening Latent Spatial Reasoning in LVLMs via Training-free Geometric Rectification
GRASP: Graph Reasoning via Agentic Solving and Probing of LLMs
Great Minds Think Alike: Contextual Tacit Communication for Decentralized LLM-Agent Cooperation
Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance
GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
Grokking Finite-Dimensional Algebra
Gromov-Wasserstein at Scale, Beyond Squared Norms
Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs
Grounding Functional Similarity by Invariance-Aware Model Stitching
Grounding LLMs in Scientific Discovery via Embodied Actions
Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization
Group Cognition Learning: Making Everything Better Through Controlled Two-Stage Agents Collaboration
Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration
Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
Group-wise Data Ordering: Enhancing Instruction Tuning of Large Language Models via Embedding Proximity
Grouter: Decoupling Routing from Representation for Accelerated MoE Training
GRPO-based Cluster Decision Agent for Unknown-$\boldsymbol{K}$ Multi-view Clustering
GRPO is Secretly a Process Reward Model
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache
GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
Guaranteed Optimal Compositional Explanations for Neurons
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
Guidance: Sentence-Level Citation Enforcement via Prefix-Tail Guidance during LLM Decoding
GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance
Guided Star-Shaped Masked Diffusion
GUI-Spotlight: Adaptive Iterative Focus Refinement for Enhanced GUI Visual Grounding
GXPO: Group Cross-Lingual Relative Policy Optimization for Code Generation
H$^2$CL: Heterogeneity-Aware Hypergraph Contrastive Learning for Robust Representation Learning
h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning
Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
Hallucination Detection from Structural Reasoning Model
Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
Hamiltonian Asymmetric Fusion: One-Way Safe Directed Refinement under Modality Imbalance
Hard-Constrained Graph Generation with Discrete-Projection Diffusion
HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
Hard Labels In! Rethinking the Role of Hard Labels in Mitigating Local Semantic Drift
Hard labels sampled from sparse targets mislead rotation invariant algorithms
Harmful Overfitting in Sobolev Spaces
Harmonized Dual Policy Improvement for Modelic Reinforcement Learning

« prev Page 51/130 next »