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
One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
One-step Latent-free Image Generation with Pixel Mean Flows
One-step Optimal Transport via Regularized Distribution Matching Distillation
One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
One Tool Is Enough: Reinforcement Learning of LLM Agents for Repository-Level Code Navigation
One-Way Policy Optimization for Self-Evolving LLMs
On Expressive Power of Floating-Point Transformers
On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
On hyperparameter tuning in general clustering problemsm
On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
On Learnability and Disambiguation of Multiclass Partial Concept Classes
Online Bayesian Experimental Design for Partially Observed Dynamical Systems
Online Change Point Detection for Multivariate Inhomogeneous Poisson Processes Time Series
Online Compatible Reward Identification from Preference Feedback
Online Conformal Prediction via Universal Portfolio Algorithms
Online Continual Learning with Dynamic Label Hierarchies
Online Contract Design With Unknown Technology
Online Fair Division with Additional Information
Online Learning and Inference for Cox Proportional Hazards Models Using Renewable Sieve Estimation
Online Learning and Inference for Cox Proportional Hazards Model Using Renewable Sieve Estimation
Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
Online Linear Programming for Multi-Objective Routing in LLM Serving
Online Packet Scheduling with Deadlines and Learning
Online Robust Reinforcement Learning with General Function Approximation
Online Rubrics Elicitation from Pairwise Comparisons
Online Social Welfare Function-based Resource Allocation
On Minimum Depth and Width of Floating-Point Neural Networks for Representing Floating-Point Functions
On Path to Multimodal Historical Reasoning: HistBench and HistAgent
On Regret Bounds of Thompson Sampling for Bayesian Optimization
On Revisiting Entropy for Identifying Mislabeled Images
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
On Structured State-Space Duality
On Testing Conditional Mean Independence for Manifold-Valued Data
On the Ability of Transformers to Verify Plans
On the Accuracy of Newton Step and Influence Function Data Attributions
On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
On the Anisotropy of Score-Based Generative Models
On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering
On the Computational Complexity of Performative Prediction
On the Convergence of Decentralized Stochastic Minimax Optimization Algorithm with Compressed Communication
On the Convergence Rate of LoRA Gradient Descent
On the Coordination of Value-Maximizing Bidders
On the Difficulty of Learning a Meta-network for Training Data Selection
On the Effect of Misspecifying the Embedding Dimension in Low-rank Network Models
On the Emergence of Implicit Curriculum in RLVR Learning Dynamics
On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models
On the Epistemic Uncertainty of Overparametrized Neural Networks
On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification
On the Expressive Power of GNNs to Solve Linear SDPs

« prev Page 79/130 next »