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
MuCO: Generative Peptide Cyclization Empowered by Multi-stage Conformation Optimization
MulFCoder: Framework-conditioned Multi-agent for MLLM-based Multi-framework Front-end Code Generation
MuLoCo: Muon is a Practical Inner Optimizer for DiLoCo
Multi-Adapter Representation Interventions via Energy Calibration
Multi-agent imitation learning with function approximation: linear Markov games and beyond
Multi-Agent Reinforcement Learning with Submodular Reward
Multi-Agent Teams Hold Experts Back
MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
Multicalibration Yields Better Matchings
Multi-Distribution Robust Conformal Prediction
MultiHal: Multilingual Dataset for Knowledge-Graph Grounded Evaluation of LLM Hallucinations
Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers
Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism
Multi-Integration of Labels Across Categories for Component Identification in Multi-trial Time Series
Multi-Label Learning with Contrastive Cluster Self-Supervision for 3D Hierarchical Semantic Segmentation
Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics
Multilingual Safety Alignment via Representation-Space Separability
Multilingual Safety Alignment Via Sparse Weight Editing
Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
Multimarginal flow matching with optimal transport potentials
Multi-marginal temporal Schrödinger Bridge Matching from unpaired data
Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling
Multimodal Fact-Level Attribution for Verifiable Reasoning
Multimodal Function Vectors for Visual Relations
Multimodal Fusion via Self-Consistent Task-Gradient Fields
Multimodal Latent Language Modeling with Next-Token Diffusion
Multimodal Meta-Verifier with Explicit Structured Recalibration
Multimodal Nested Learning for Decoupled and Coordinated Optimization
Multimodal Scaling Laws for Task & Data-Optimized Models of Visual Cortex
Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraint Decomposition
Multi-Objective Bayesian Optimization via Adaptive $\varepsilon$-Constraints Decomposition
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models
Multi-Objective Protein Design via Memory-Aware Test-Time Scaling in Diffusion Models
Multiple Choice Learning of Low-Rank Adapters for Language Modeling
Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
Multirate training of neural networks
Multi-Round Human–AI Collaboration with User-Specified Requirements
Multi-scale Explainer for Graph Neural Networks
Multi-Scale Wavelet Transformers for Operator Learning of Dynamical Systems
Multi-Task Bayesian In-Context Learning
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety
Multi-timescale Reinforcement Learning by Value Reconstruction
Multivariate Distributional Reinforcement Learning Using Sliced Divergences
Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms
Multi-view Consistent Latent Action Learning for World Modeling and Control

« prev Page 74/130 next »