Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 250
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published May 26 • 144
Data-Gouv-ML/recensement-des-equipements-sportifs-a-paris-idf Viewer • Updated 14 days ago • 2.91k • 85 • 1
Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces Paper • 2605.14786 • Published May 14 • 2
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published May 14 • 147
It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs Paper • 2605.20258 • Published May 18 • 30
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Paper • 2605.18401 • Published May 18 • 130
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Paper • 2605.06130 • Published May 7 • 116
OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents Paper • 2605.05185 • Published May 6 • 106
Better Models, Faster Training: Sigmoid Attention for single-cell Foundation Models Paper • 2604.27124 • Published Apr 29 • 11
Geometric coherence of single-cell CRISPR perturbations reveals regulatory architecture and predicts cellular stress Paper • 2604.16642 • Published Apr 17 • 6