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
Seeing the Unseen: Physics-as-Representation for Generalizable Gaze Perception
Seeing to Generalize: How Visual Data Corrects Binding Shortcuts
Seeing Without Understanding: Disentangling Perception, Reasoning, and Simulation in VLM Gameplay
Seeking Commonality, Preserving Specificity: A Spectral-Aware Hierarchical Framework for Cross-City Road Representation Learning
See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling
SEER: Transformer-based Robust Time Series Forecasting via Automated Patch Enhancement and Replacement
See the Emotion: A Facial Emoji Proxy Modeling for EEG Emotion Recognition
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
SE-GA: Memory-Augmented Self-Evolution for GUI Agents
Segment-Aligned Policy Optimization for Multi-Modal Reasoning
Segment Anything with Robust Uncertainty-Accuracy Correlation
Segment-driven Structural Induction and Semantic Alignment for Heterogeneous Tabular Representation
SegPVSG: Panoptic Video Scene Graph Generation via Temporal Focusing and Generative Augmentation
Seg-ReSearch: Segmentation with Interleaved Reasoning and External Search
SeisMark: A Large-Scale Open Benchmark for Robust 3D Seismic Fault Detection
Seizure-Semiology-Suite($S^3$): A Clinically Multimodal Dataset, Benchmark, and Models for Seizure Semiology Understanding
Selecting Samples on Graphs: A Unified Dataset Pruning Framework for Lossless Training Acceleration
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
Selective Deferred Routing: Enabling Cost-Efficient Collaboration between Local SLMs and Remote LLMs
Selective Disclosure Watermarking for Large Language Models
Select to Think: Unlocking SLM Potential with Local Sufficiency
Self-Augmenting Retrieval for Diffusion Language Models
Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models
Self-correcting for Debiasing Large Language Models
Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation
Self-Distillation Enables Continual Learning
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Self-evolving LLM agents with in-distribution Optimization
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning
Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Edit via In-Context Learning
Self-Prophetic Decoding to Unlock Visual Search in LVLMs
Self-Refining Video Sampling
Self-Soupervision: Cooking Model Soups without Labels
Self-Supervised Dynamical System Representations for Physiological Time-Series
Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
Self-Supervised Foundation Model for Calcium-imaging Population Dynamics
Self-supervised Hierarchical Visual Reasoning with World Model
Self-Supervised Learning as Discrete Communication
Self-Supervised Weight Templates for Scalable Vision Model Initialization
Selling Data as a Digital Good with Scaling Valuations
SEMA: a Scalable and Efficient Mamba like Attention via Token Localization and Averaging
Semantic-Aware Motion Encoding for Topology-Agnostic Character Animation
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
Semantic Editing with Coupled Stochastic Differential Equations
Semantic-Enriched Latent Visual Reasoning
Semantic Granularity Navigation in Image Editing

« prev Page 102/130 next »