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
Strategy-Aware Optimization Modeling with Reasoning LLMs
Strategy Executability in Mathematical Reasoning: Leveraging Human–Model Differences for Effective Guidance
Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation
Streaming Covariate Balancing via Discrepancy-Based Feature Coresets
Streaming Sliced Optimal Transport
Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage
StretchTime: Adaptive Time Series Forecasting via Symplectic Attention
STRIDE: Post-Training LLMs to Reason and Refine Bio-Sequences via Edit Trajectories
Stronger Benchmarks for Prediction as a Service with Constraints
StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose Estimation
StructMAR: Structure-Aware Masked Autoregression for Explicit Layout Alignment in Text-to-Image Generation
Structurally Aligned Subtask-Level Memory for Software Engineering Agents
Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model
Structure-Aware Consistency Priors for Shape from Polarization in Complex Media
Structure-aware Granular-Ball based Information Bottleneck for Multi-modal Clustering
Structure-Aware Riemannian Flow Matching for Registration and Fusion of Hyperspectral and Multispectral Images
Structure-Centric Graph Foundation Model via Geometric Bases
Structured 4D Latent Predictive Model for Robot Planning
Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
Structured Expert Routing with Multi-View Task Priors for Offline Meta-Reinforcement Learning
Structured Multi-modal Graph Disentanglement for Psychiatric Diagnosis
Structured Multi-step Jailbreaking under a Hamiltonian Generative Formulation
Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
Structure Enables Effective Self-Localization of Errors in LLMs
Structure-Induced Information for Rerooting Levin Tree Search
Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
STT-LLM: Structural-Temporal Tokenization for Adapting LLMs to Longitudinal Clinical Profiles
Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
ST-Veto: Spatio-Temporal Token Veto for Diffusion MLLMs via Taylor Prediction and Visual Grounding
StyleDistillation: A New Insight of Image Style Enables Personalized Aesthetic Manipulation
Subgroup Discovery with the Cox Model
Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
Submodular Optimization for Minimal Augmentation in Robust Language Model Alignment
Subspace-Aware Feature Reshaping for Open-Set Graph Class-Incremental Learning
SubspacePath Pruner: Inference-time Pruning via Probe-based Representation–Parameter Coupling
Subtle Topic Models and Discovering Subtly Manifested Software Concerns Automatically
Success-Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
SuperHype: Hypergraph Generation via Graph-Superposition Decomposition
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
Supervised Graph Contrastive Learning for Gene Regulatory Networks
Supervised Guidance Training for Infinite-Dimensional Diffusion Models
Supervise Less, See More: Training-free Nuclear Instance Segmentation with Prototype-Guided Prompting
Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
Suppress and Diversify: Refining Robust Pathways for Corruption Robustness
SURF: Separation via Unsupervised Remixing Flow
SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate

« prev Page 110/130 next »