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
Training–Inference Consistent Segmented Execution for Long-Context LLMs
Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
Training LLM Agents to Empower Humans
Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning
Training-Trajectory-Aware Token Selection
Training with Honeypots: Reshaping How LLMs Fail Under Adversarial Attacks
Train Once, Reuse Everywhere: Generalizable Implicit ICL by Routing Attention
Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention
Trajectory-Aware Certified Decentralized Unlearning via SGD Stability
Trajectory-Aware Heuristic Learning for Combinatorial Search
Trajectory-Aware Spiking DiTs Conversion via Membrane Potential Error-Feedback
Trajectory Consistency for One-Step Generation on Euler Mean Flows
Trajectory-Level Data Augmentation for Offline Reinforcement Learning
Trajectory-Level Speculative Decoding for Diffusion Language Models
Trajectory Seriation via Spectral Tangent Alignment and Global Embedding
Trajectory-Stabilized Inference for Diffusion-Based Video Inpainting
Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
Transcriptomics-Conditioned Virtual Tissue Synthesis via Diffusion Transformers
Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment
Transfer Learning in High-dimensional Ising Models
Transfer Learning in Nonparametric Regression with Deep ReLU Networks
Transformed Latent Variable Multi-Output Gaussian Processes
Transformer Circuits Can Realize Clustering Algorithms
Transformers Can Learn Posterior Predictive Distributions In-Context
Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent
Transformers learn factored representations
Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data
Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently
Transforming Weather Data from Pixel to Latent Space
Transform Trained Transformer for Accelerating Native 4K Video Generation
Transitive Representation Learning Enhances Histopathology Annotation
Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment
Translation Heads: Disentangling meaning from language in LLM-based machine translation
TransLight: Image-Guided Customized Lighting Control with Generative Decoupling
TransNormal: Dense Visual Semantics for Diffusion-based Transparent Object Normal Estimation
Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
Transport and Merge: Cross-Architecture Merging for Large Language Models
Transport Clustering: Solving Low-Rank Optimal Transport via Clustering
Transporting Task Vectors across Different Architectures without Training
Transport or Discard: Robust Unbalanced Optimal Transport for Cross-Domain Policy Adaptation
TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection
TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
Treatment Responder Classification with Abstention
TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution
TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

« prev Page 120/130 next »