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
Two-Stage Unit Tying for Simplifying Differentiable Logic Gate Networks
U$^3$CF: Unbiased, Unconfounding, and Unified Causal Framework for Multi-Target Domain Adaptation
UAV$^2$: A Unified and Adaptive Scheduling Framework for UAV Autopilot Systems with Reinforcement Learning
UAV$^2$: A Unified and Adaptive Scheduling Framework for UAV Autopilot System with Reinforcement Learning
Ubiquity of Emergent Hebbian Dynamics in Regularized Learning
UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models
U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster
UCPO: Uncertainty-Aware Policy Optimization
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
UGround: Towards Unified Visual Grounding with Unrolled Transformers
UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
UI2Code$^{\text{N}}$: UI-to-Code Generation as Interactive Visual Optimization
UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization
Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov–Arnold Networks
UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
UltraHorizon: Benchmarking LLM-Agent Capabilities in Ultra Long-Horizon Scenarios
UltraLIF: Fully Differentiable Spiking Neural Networks via Ultradiscretization and Max-Plus Algebra
UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
Unbiased Alignment for Large Language Models with Noisy Preferences
Unbiased and Second-Order-Free Training for High-Dimensional PDEs
Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
Unbiased Principles, Robust Rewards
Unbiased Reward Modeling from Implicit Feedback for LLM Alignment
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Uncertainty-Constrained Trustworthiness for Graph Learning
Uncertainty-Guided Exploration and Stable Planning for Sparse-Reward Manipulation from Limited Demonstrations
Uncovering Bias Mechanisms in Observational Studies
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
Uncovering Grounding IDs: How External Cues Shape Multi-Modal Binding
Uncovering Hidden Triggers: Backdoor Attribution in Language Models
Uncovering Latent Communication Patterns in Brain Networks via Adaptive Flow Routing
Uncovering the Gradient Geometry of Long CoT: A Spectral-guided Approach to Reasoning Distillation
Uncovering the Latent Potential of Deep Intermediate Representations
Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Understanding Behavior Cloning with Action Quantization
Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics
Understanding Data Temporality Impact on Large Language Models Pre-training
Understanding Dynamic Compute Allocation in Recurrent Transformers
Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
Understanding Generalization and Forgetting in In-Context Continual Learning
Understanding Generalization from Embedding Dimension and Distributional Convergence
Understanding LoRA as Knowledge Memory: An Empirical Analysis
Understanding MARS: When Scaling Momentum Correction Provably Helps
Understanding MARS: When Scaling Momentum Provably Helps
Understanding Multimodal Learning: A Loss Landscape Smoothness Perspective
Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions
Understanding Private Learning From Feature Perspective
Understanding SAM through Minimax Perspective

« prev Page 122/130 next »