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
Convolutional Learnable-Group Weightless Neural Network
Cooperative Variance Estimation and Bayesian Neural Networks for Disentangling Aleatoric and Epistemic Uncertainties
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations
CooT: Learning to Coordinate In-Context with Coordination Transformers
CoPE: A Framework for Optimizing Coordination between Planning and Execution in LLM-based Agents
CoPE: Continual Probe-guided Expansion for Large Vision-Language Models
COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs
Copula-SVI: Vine-Copula Variational Inference with Stein Refining for Instance-Level Correlation Capturing
Copyright-Bench: Agentic Evaluation of Copyright Law Compliance
CORAL: Uncertainty-Aware Regulation of Exposure Concentration in Recommender Systems
CoRe: Collaborative Reasoning via Cross Teaching
CoRe: Combined Rewards with Vision-Language Model Feedback for Preference-Aligned Reinforcement Learning
CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
CORE: Context-Robust Remasking for Diffusion Language Models
Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
CORE-MTL: Rethinking Gradient Balancing via Causal Orthogonal Representations
CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
Corrected Samplers for Discrete Flow Models
Correcting in Hindsight: Editing Past Key-Value States for Robust LLM Reasoning
Correcting Overparameterization Effects in Fair Empirical Risk Minimization
Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference
Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory
CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
Correctness-Optimized Residual Activation Lens (CORAL): Transferable and Calibration-Aware Inference-Time Steering
Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering
Correspondence Cognitive Learning for Multi-Modal Object Re-Identification
Corrigibility Transformation: Constructing Goals That Accept Updates
CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates
Cost-aware Stopping for Bayesian Optimization
CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
Counterfactual Bootstrap for Robust Meta-Reinforcement Learning
Counterfactual Occlusion-Aware Learning via Visibility Intervention for LiDAR Anomaly Detection
Counterfactual Residual Data Augmentation for Regression
CountsDiff: A diffusion model on the natural numbers for generation and imputation of count-based data
Coupled Cluster con MoLe: Molecular Orbital Learning for Neural Wavefunctions
Coupled Training with Privileged Information and Unlabeled Data
Coupled Trigger Optimization and Vulnerable Parameter Alignment for Persistent Backdoor Attacks on Federated Learning
Coupled Variational Reinforcement Learning for Language Model General Reasoning
Courtroom Analogy: New Perspective on Uncertainty-Aware Classification
Covariance estimation using Markov chain Monte Carlo
Covariance Volume Maximization for Embodied Latent Exploration in Deep Reinforcement Learning
Coverage ≠ Exposure: Auditable Control of Same-Support Tail Failures under Multimodal Missingness
Coverage Improvement and Fast Convergence of On-policy Preference Learning
Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
CoverPruneGS: Coverage-Preserving Structured Pruning for Compact 3D Gaussian Splatting from Sparse-View Monocular Videos
CoverPruneGS: Coverage-Preserving Structured Pruning for Hierarchical 3D Gaussian Splatting from Sparse-View Monocular Videos
CPMöbius: Iterative Coach–Player Reasoning for Data-Free Reinforcement Learning

« prev Page 24/130 next »