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
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
Revealing Long-context Potential of Attention Heads via Frequency Kernels
Revealing Scaling Paradox in Large-scale Time Series Models: Implications for More Efficient and Accurate Forecasting
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
Revenue Guarantees of No-Swap-Regret Dynamics in First Price Auctions
Reverse-Engineering Model Editing on Language Models
Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
Revisiting Asymmetries in Black-box Link Stealing against Graph Neural Networks
Revisiting Coding-Based Approaches to Overcome the Curse of Dimensionality in Learning-Based Watermarking
Revisiting Distribution Correction Estimation for Offline Imitation Learning with Suboptimal Dataset
Revisiting Efficiency–Accuracy Scaling in Mixture-of-Experts Architectures
Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms
Revisiting Neural Processes via Fourier Transform and Volterra Series
Revisiting OOD Generalization in Programmatic RL
Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
Revisiting Spectral Representations in Generative Diffusion Models
Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
Revisiting the Role of Pretrained Weights in Model Merging: On Near-Optimality within the Core Subspace
Revisiting the Volume Hypothesis
Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval
Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
REVIS: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
ReViT: Rotational-equivariant Vision Transformers for Neural PDE Solvers
REViT: Roto-reflection Equivariant Convolutional Vision Transformer
Reviving Error Correction in Modern Deep Time-Series Forecasting
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios
Reward-free Alignment for Conflicting Objectives
Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
Reward Learning through Ranking Mean Squared Error
Reward Modeling from Natural Language Human Feedback
Reward-Preserving Counterfactual State Editing for Offline Reinforcement Learning
Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity
Reward Shaping Control Variates for Off-Policy Evaluation Under Sparse Rewards
Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models
Rewiring Experts on the Fly: Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert Models
Rex: A Family of Reversible Exponential (Stochastic) Runge-Kutta Solvers
RGGT: A Generative-Prior-Guided Transformer for Unified Rigid and Non-Rigid Point Cloud Registration
RGMem: Renormalization Group–inspired Memory Evolution for Language Agents
Rh-3DGS: Robust Open-Vocabulary Scene Understanding via Riemannian Huber Distillation and Manifold-Aware Sampling

« prev Page 96/130 next »