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
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
Towards Theoretical Understanding of Transformer Test-Time Computing: Investigation on In-Context Linear Regression
Towards the Training of Deeper Predictive Coding Neural Networks
Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts
Towards Trustworthy and Identifiable Virtual Face Generation
Towards Trustworthy Video Anomaly Understanding: A Class-Guided Chain-of-Evaluation Metric and An Anomaly-focused Meta-Benchmark
Toward Subspace-Perturbed Trajectory-Aware Backdoor Attacks in Deep Reinforcement Learning
Towards Understanding Adam Convergence on Highly Degenerate Polynomials
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
Towards Understanding Generalization of Federated Adversarial Learning: Perspective of Algorithmic Stability
Towards Understanding Massive Activations in Attention Sink Mechanism
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
Towards Understanding Steering Strength
Towards Understanding the Dynamics of Low-Rank Adaptation
Towards Uniformity and Alignment for Multimodal Representation Learning
Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models
Towards Whole-corpus Reconstruction of Heterogeneous RAG Knowledge Bases
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
Toward Understanding Adversarial Distillation: Why Robust Teachers Fail
TPGDiff : Hierarchical Triple-Prior Guided Diffusion for Image Restoration
T-POP: Test-Time Personalization with Online Preference Feedback
TPV: Parameter Perturbations Through the Lens of Test Prediction Variance
TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention
TRACER: Persistent Regularization for Robust Multimodal Finetuning
TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning
TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels
TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation
TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning
Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
Tracing the Persona Circuit: How Large Language Models Encode and Express Character Traits
Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
Tractable Expected Information Gains for Exponential Family Posteriors
Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
Trainable Nonexpansive Denoisers for Contractive Image Reconstruction
Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
Training AI Co-Scientists Using Rubric Rewards
Training Data Efficiency in Multimodal Process Reward Models
Training Deep Spiking Neural Networks without Normalization
Training Diffusion Language Models for Black-Box Optimization
Training-Free Adaptation of Diffusion Models via Doob's $h$-Transform
Training-Free Adversarial Robustness in Computational MRI
Training-Free Bayesian Filtering with Generative Emulators
Training-Free Coverless Multi-Image Steganography with Access Control
Training-Free Guided Diffusion for Planning: A Unified Framework via Doob’s h-Transform with Safety Guarantees
Training-Free Hashing-Based Attention via Binary Principal Components
Training-Free Multimodal Large Language Model Orchestration
Training-Free Rate-Distortion-Perception Traversal With Diffusion
Training-Free Vector Quantization via Gaussian VAEs

« prev Page 119/130 next »