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
An Approximation Algorithm for Graph Label Selection
A Narrowing Geometry in Contaminated Reasoning
An Asymmetric Latent Factorization-of-Tensors Model for Relation Analysis
Anatomy of Massive Activations and Attention Sinks
ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models
ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model
Anchored Policy Optimization: Mitigating Exploration Collapse via Support-Constrained Rectification
Anchored Self-Play for Code Repair
Anchor-Final Self-Supervision Drives Hallucination-Aware Optimization in Large Vision-Language Models
Anchor-guided Hypergraph Condensation with Dual-level Discrimination
Anchoring Self-Play for Code Repair
An Efficient Joint Learning Approach for Item Response Theory
An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
An Empirical Study on the Resilience of Partial Merging to Model Clone Attacks
An Evidential Route to Asymptotic Bayes Optimality under Sparsity
A New Framework for Cybersecurity Refusals in AI Agents
An Exploration of Non-Euclidean Gradient Descent: Muon and its Many Variants
An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
An Exterior Method for Nonnegative Matrix Factorization
Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
An In-Depth Study on Deep Learning Model Cloning
An Information-Theoretic Criterion for Efficient Data Synthesis
An Interactive Paradigm for Deep Research
Annotations Mitigate Post-Training Mode Collapse
An Odd Estimator for Shapley Values
A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
Anomaly-Preference Image Generation
AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
Anti-Aliasing Matters: A Dynamic Network for Time Series Forecasting
Anti-Backdoor Coreset Selection via Cumulative Entropy
ANTiC: Adaptive Neural Temporal In Situ Compressor
Anti-causal domain generalization: Leveraging unlabeled data
Antidistillation Fingerprinting
Any2Any: Unified Arbitrary Modality Translation for Remote Sensing
Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
AnyBand-Diff: A Unified Remote Sensing Image Generation and Band Repair Framework with Spectral Priors
AnyCanvas: Potential Field Guidance for Training-Free Spatial Control in Text-to-Image Diffusion
Any-dimensional invariant universality
AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
Anytime Detection of Strategic Deviations in Multi-Agent Systems
Anytime Safe PAC Efficient Reasoning
Anytime-Valid Inference for Online Ranking of Large Language Models
AOEB: Benchmarking Agent-Oriented Multimodal Embeddings
AOEPT: Breaking the Implicit Modality-Reduction Bottleneck in Modality-Missing Prompt Tuning
AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration
APE-Bench: Evaluating Automated Proof Engineering for Formal Math Libraries
A Penalty Approach For Differentiation Through Black-box Quadratic Programming Solvers

« prev Page 7/130 next »