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
Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
Contextual Slate GLM Bandits with Limited Adaptivity
Continual GUI Agents
Continual Learning of Domain-Invariant Representations
Continual Learning through Control Minimization
Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe
Continual Model Routing in Evolving Model Hubs
Continual Segmentation under Joint Nonstationarity
Continuity-Regularized Flow Matching for Offline Reinforcement Learning
Continuous Diffusion Models Can Obey Formal Syntax
Continuous-Time Piecewise-Linear Recurrent Neural Networks
Continuous Variable Hamiltonian Learning at Heisenberg Limit via Displacement-Random Unitary Transformation
Continuous Viewpoint Adaptation for Single View 3D Object Reconstruction
CONTINUUM: Restoring the Contiguous Tensor Abstraction Efficiently for Dynamic AI Workloads via Hardware Virtualization
Contractive Anchor Resolvent Diffusion for Incomplete Multi-View Clustering
ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts
Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation
Contrastive Flow Map Matching
Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design
Contrastive Image-Metadata Pre-Training for Materials Transmission Electron Microscopy
Contrastive Order Learning: A General Framework for Ordinal Regression
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
Contrastive Representation Regularization for Vision-Language-Action Models
Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
Contrastive Symbolic Regression: Aligned Representations, Adaptive Prediction, and Diverse Ensembles
Contrastive Weak-to-Strong Generalization
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
Control Consistency Losses for Diffusion Bridges
Controllable and Explainable Personality Sliders for LLMs at Inference Time
Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective
Controlled Collaboration Geometry for Personalized Federated Learning
Controlled Dynamics Attractor Transformer
Controlled LLM Training on Spectral Sphere
Controlled SDEs for Long-Horizon Motion Generation under Latent Decision Uncertainty
Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation
Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel Optimization
Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
Convergence of Steepest Descent and Adam under Non-Uniform Smoothness
Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning
Convergence Rate Analysis of the AdamW-Style Shampoo: Unifying One-Sided and Two-Sided Preconditioning
Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
Convergent World Representations and Divergent Tasks
Conversation for Non-verifiable Learning: Self-Evolving Large Language Models through Meta-Evaluation
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
ConvexBench: Can LLMs Recognize Convex Functions?
Convex Dataset Valuation for Post-Training
Convex Distance Operator Transport: A Convex and Geometry-Preserving Formulation
Convex Low-resource Accent-Robust Language Detection in Speech Recognition
Convex Optimization for Alignment and Preference Learning on a Single GPU

« prev Page 23/130 next »