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
From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers
From Knowledge to Inference: Formalizing Specialized Public Health Reasoning on GlobalHealthAtlas
From LLM-Generated Conjectures to Lean Formalizations: Automated Polynomial Inequality Proving via Sum-of-Squares Certificates
From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax Optimization
From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
From Moments to Models: Graphon-Mixture Learning for Mixup and Contrastive Learning
From Muon to Gluon: Bridging Theory and Practice of LMO-based Optimizers for LLMs
From Noise to Control: Parameterized Diffusion Policies
From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges
From Observations to States: Latent Time Series Forecasting
From Optimization to Generalization under Heavy-Tailed Data: The Role of Gradient Clipping
From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training
From Out-of-Distribution Detection to Hallucination Detection: A Geometric View
From Parameter Dynamics to Risk Scoring: Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging
From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning
From Per-Image Low-Rank to Encoding Mismatch: Rethinking Feature Distillation in Vision Transformers
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning
From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
From Representation to Action: A Unified Laplacian Framework for Spatial Representation and Path Planning
From Retrieval to Translation: Translating Query into Graph-level Clues for Retrieval-Augmented Generation
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors
From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection
From Teacher Pathways to Invariant Manifolds: Consensus Subspace Distillation for TSFMs
From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction
From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents
From Welfare to Utility: Generalized Objectives in Budget-Feasible Procurement
From Winning to Understanding: A Diagnostic Long-Horizon RTS Benchmark for LLMs
From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
FrontierCS: Evolving Challenges for Evolving Intelligence
Frontier Models Can Take Actions at Low Probabilities
Front-Loaded Robust Conformal Prediction: Heavy Calibration, Minimal Test-Time Cost
FS-I2P: A Hierarchical Focus–Sweep Registration Network with Dynamically Allocated Depth
FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents
Full-Batch Gradient Descent Outperforms One-Pass SGD: Sample Complexity Separation in Single-Index Learning

« prev Page 46/130 next »