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
HieRD: Hierarchical Relational Distillation for Vision-Language Embedding Models
High-accuracy and dimension-free sampling with diffusions
High-Accuracy Sampling for Diffusion Models and Log-Concave Distributions
High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent Confounders
Higher-Order Certified Robustness for Regression
High-Fidelity ANN-to-SNN Conversion via Closed-Loop CKA Distillation
High-Probability Convergence Guarantees of Decentralized SGD
HilbertA: Hilbert-Curve–Aligned Sparse Attention for 2D Structured Data
HiMAP-Travel: Hierarchical Multi-Agent Planning for Long-Horizon Constrained Travel
HiMe: Hierarchical Embodied Memory for Long-Horizon Vision-Language-Action Control
HInT: Hypergraph Infusion at the Structural Layers Improves Table Understanding
HiPER: Hierarchical Plan–Execute RL for Multi-Turn LLM Agents
HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?
HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models
Hista and Numca: Estimate State Value Effectively for Large Language Model Reinforcement Learning
HiST: A Hierarchical Sparse Transformer for Cross-Modal Spatial Transcriptomics Modeling
History-Bootstrapped Flow Matching for Inverse Boiling Reconstruction
Hi-Time: Hierarchical Latent Prediction for Multivariate Time Series Classification
HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
HOBIT: Hardness Optimized Batch Sampling for InfoNCE Training
HodgeFlow Policy Search by Topologically Dissecting Temporal-Difference Signals in Non-Markovian Environments
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
Hölder++: Improving Quality-Coherence Trade-off in Multimodal VAEs
Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence
HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing
Holonomy Grid Codes for Generalisation Under Directed Actions
Homophily-Heterogeneity Gradient Surgery for Federated Graph Learning
Hom-PGD$^+$: Fast Reparameterized Optimization over Non-convex Ball-Homeomorphic Set
HONet: Data-Efficient Learning for Exact Cover Tasks via Hypergraph Optimization
HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
How2Everything: Mining the Web for How-to Procedures to Evaluate and Improve LLMs
How can embedding models bind concepts?
How Can Mamba Learn In Context with Outliers and Generalize Provably?
How can we assess human-agent interactions? Case studies in software agent design
How does Bayesian Sampling help Membership Inference Attacks?
How does Chain of Thought decompose complex tasks?
How does information access affect LLM monitors' ability to detect sabotage?
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off
How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
How Do Language Models Speak Languages? A Case Study on Unintended Code-Switching
How do LLMs Compute Verbal Confidence?
How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning
How Far Can LLM Agents Reason with Tables? Benchmarking Multi-Turn Agentic Table Question Answering in the Wild
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
How Good is Post-Hoc Watermarking With Language Model Rephrasing?
How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning

« prev Page 53/130 next »