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
QuITE: Query-Based Irregular Time Series Embedding
R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations
R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?
R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning
R2-Router: A New Paradigm for LLM Routing with Reasoning
RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference
RaBiT: Residual Aware Binarization Training for Accurate and Efficient LLMs
RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models
RADAR: Defending RAG Dynamically against Retrieval Corruption
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
RADE: Random Add-Drop Edge as a Regularizer
RA-Det: Towards Universal Detection of AI-Generated Images via Robustness Asymmetry
Radial Scaling Voxelization for Accurate Small Object 3D Detection
RADIO1D: Elastic Representations for Condensed Vision Modeling
RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
RAGEN-2: Reasoning Collapse in Agentic RL
RaGEP: Rank-aware Geometric Expert Pruning for Mixture-of-Experts Language Models
RAG without Forgetting: Continual Query-Infused Key Memory
RAIGen: Rare Attribute Identification in Text-to-Image Generative Models
RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization
Ramba: Selective State-Space Models for Relational Deep Learning
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
Randomized Feasibility Methods for Constrained Optimization with Adaptive Step Sizes
Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields
Random Scaling of Emergent Capabilities
Random Selection Reveals Implicit Knowledge Consensus in Code Generation
Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
Rank-guided Diffusion for Noise Few-Shot Learning
Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains
Ranking Time Series using a Time Warping Ideal Point Model
Rank-Learner: Orthogonal Ranking of Treatment Effects
Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
Rare Event Analysis of Large Language Models
RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-Hailing
Rate or Fate? RLV$^{\varepsilon}$R: Reinforcement Learning with Verifiable Noisy Rewards
Rationality Measurement and Theory for Reinforcement Learning Agents
Rational Neural Networks have Expressivity Advantages
Rational Transductors
Ratio-Variance Regularized Policy Optimization
RAT+: Train Dense, Infer Sparse - Recurrence Augmented Attention for Dilated Inference
RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
Rays as Pixels: Learning A Joint Distribution of Video and Camera Trajectories
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories
RBCBF: Decoding Time Safety Alignment via Risk Guided Rollback and Barrier Control
RC-FCL: Combating Asynchronous Concept Drift in Federated Continual Learning via Retrospective Calibration
R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting
Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design

« prev Page 91/130 next »