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
Understanding Self-Supervised Learning via Latent Distribution Matching
Understanding the Ability of LLMs to Handle Character-Level Perturbation
Understanding the Gaps in Satisficing Bandits
Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
Understanding the Parameter Space Volume of Transformers Encoding Boolean Functions
Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
Understanding Transfer Learning of RNA Foundation Models on Downstream Tasks
Understanding Truncated Positional Encodings for Graph Neural Networks
Unfolded Laplacian Spectral Embedding: A Theoretically Grounded Approach to Dynamic Network Representation
Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving Linearization
UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
UniCode: Augmenting Evaluation for Code Reasoning
Uni-DocRobust: Universal Plug-and-Play Robustness Enhancement for Multi-modal LLMs via Feature Restoration
UniDrag: Unified Multi-Field Prediction and Robust Shape Optimization for Vehicle Aerodynamics
UniFast-HGR: Scalable and Efficient Maximal Correlation for Multimodal Models
Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification
Unified Multimodal Visual Tracking with Dual Mixture-of-Experts
Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
Unified Time Series Explanations via Amortized Optimization and Instance-level Multi-Expert Knowledge Distillation
UniFLoW: Universal Multi-Modal Federated LoRA Fine-Tuning Framework with Analytical Aggregation
Unifying Adversarial Robustness and Training Across Text Scoring Models
Unifying and Optimizing Data Values for Selection via Sequential Decision-Making
Unifying Dataset Pruning and Distillation for Efficient Large-scale Compression
Unifying Deep Stochastic Processes for Image Enhancement
Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration
Unifying Heterogeneous Multi-Modal Remote Sensing Detection Via Language-Pivoted Pretraining
Unifying Low Dimensional Spectra in Deep Learning
Unifying Masked Diffusion Models with Various Generation Orders and Beyond
Unifying Stacking and Cascading for Efficient Ensemble Inference
Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets
UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
UniMapping: Unified SLAM Framework for Map-Centric Embodied Perception
UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis
UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture
UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling
Unison: Benchmarking Unified Multimodal Models via Synergistic Understanding and Generation
UniSparse: Combining Weight Pruning and Spike Sparsification in Spiking Neural Networks
UniSVQ: 2-bit Unified Scalar-Vector Quantization
Unitary Convolutions for Message-passing and Positional Encodings on Directed Graphs
Universal Algorithm-Implicit Learning
Universal Approximation with Softmax Attention
Universal Learning of Nonlinear Dynamics
Universal Multiclass Transductive Online Learning
Universal One-third Time Scaling in Learning Peaked Distributions
Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
Universal Redundancies in Time Series Foundation Models
Universal Representation of Generalized Convex Functions and their Gradients
Universal Skeleton Understanding via Differentiable Rendering and MLLMs

« prev Page 123/130 next »