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
Semantic Impact–Driven Visual Scheduling for Vision Language Models
Semantic Impact–Driven Visual Scheduling in Vision-Language Models
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
SemanticNVS: Improving Semantic Scene Understanding in Generative Novel View Synthesis
Semantic Robustness Certification for Vision-Language Models
Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks
Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews
Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees
Semi-LAR: Semi-supervised Contrastive Learning with Linear Attention for Removal of Nighttime Flares
SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
Semi-Supervised Gaze Estimation via Disentangled Subspace Contrastive Learning
Semi-Supervised Hypothesis Testing by Betting on Predictions
Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
Semi-Supervised Neural Super-Resolution for Mesh-Based Simulations
Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain
SemRep : Generative Code Representation Learning with Code Transformations
SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework
SE(n)-Invariant Flow Matching: A General Framework with Application to Object Reassembly
Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
Separating Representation from Reconstruction Enables Scalable Text Encoders
SEPS: Semantic-Enhanced Patch Slimming Framework for Fine-Grained Cross-Modal Alignment
Sequential Group Composition: A Window into the Mechanics of Deep Learning
Sequential Kernel-based Conditional Independence Testing via Adaptive Betting
SERA: Soft-Verified Efficient Repository Agents
Server-Proximal Aggregation for Federated Domain-Incremental Learning under Partial Participation: Task-Uniform Convergence and Backward Transfer
Set-Coupled Guidance: Set-Level Coordination in Diffusion-Based Dataset Distillation
Set Diffusion: Interpolating Token Orderings between Autoregression and Diffusion for Fast and Flexible Decoding
SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning
Set-Preserving Calibration from Conformal P-Values to E-Values
SFCLTA: Spectral Fusion Contrastive Learning with Topology-Adaptive Graph Augmentation
SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts
SF-Mamba: Rethinking State Space Model for Vision
SG2Loc: Sequential Visual Localization on 3D Scene Graphs
SGERA: Stein-Guided ECG-Report Alignment for ECG Representation Learning
SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation
ShapCCS: Shapley-Driven Client Coreset Selection in Federated Learning
Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought
SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning
Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
Shapley Regularized Neural Granger Causality
Shared Lexical Task Representations Explain Behavioral Variability In LLMs
Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
Sharp Concentration Bounds for Bundle-Valued Statistics on Manifolds
Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
Sharp Empirical Bernstein Inequalities for the Variance of Bounded Random Variables
Sharper Generalization Guarantees for Asynchronous SGD: Beyond Lipschitzness, Smoothness and Data Homogeneity

« prev Page 103/130 next »