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
Rethinking Calibration for Early-Exit Neural Networks
Rethinking Code Complexity Through the Lens of Large Language Models
Rethinking Contrastive Learning for Graph Collaborative Filtering: Limitations and a Simple Remedy
Rethinking Convergence in MoE Training: The Role of Routing Sparsity
Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective
Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle
Rethinking Evaluation Paradigms in IBP-based Certified Training
Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
Rethinking Federated Prompt Learning for Medical Images: From Textual Tuning to Visual Manifold Anchoring
Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective
Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?
Rethinking Genomic Modeling Through Optical Character Recognition
Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution
Rethinking Graph Transformers as Graph Signal Denoisers: The Role of Block-Diagonal Priors
Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
Rethinking Instruction Drift as a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
Rethinking LLM Ensembling from the Perspective of Mixture Models
Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
Rethinking Low-Confidence Pseudo Labels: Influence-Aware Semi-Supervised Fine-Tuning for Hyperspectral Change Detection
Rethinking Multimodal Time-Series Forecasting Evaluation
Rethinking Neural Network Learning Rates: A Stackelberg Perspective
Rethinking Parameter Sharing as Graph Coloring for Structured Compression
Rethinking Personalization in Large Language Models at the Token Level
Rethinking Pretraining Data Detection for LLMs: From Local to Global
Rethinking Serialization in Linear 3D Vision: Decoupling Anisotropic Geometry from Isotropic Semantics
Rethinking Sparse Mixture of Experts from a Unified Perspective
Rethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence
Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
Rethinking the Flow-based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective
Rethinking the Hardness of PbRL: A Provable General Regret Bound
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
Rethinking the Trust Region in LLM Reinforcement Learning
Rethinking Thinking Tokens: LLMs as Improvement Operators
Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution
Rethinking Video Generation Model for the Embodied World
Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
Rethinking Visual Intelligence: Insights from Video Pretraining
Rethink the Role of Neural Decoders in Quantum Error Correction
RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
Retrieval-Aware Distillation for Transformer-SSM Hybrids
Retriever Portfolios: A Principled Approach to Adaptive RAG
Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis
RetrOrchestrator: A Multi-Step Retrosynthesis Agent Dynamically Orchestrating Single-Step Transition Models
Return-Critic: Bridging Goal Discrepancy for Efficient Visual Reinforcement Learning
Return of Frustratingly Easy Unsupervised Video Domain Adaptation
Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
Reusing Trajectories in Policy Gradients Enables Fast Convergence

« prev Page 95/130 next »