VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published 6 days ago • 23
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization Paper • 2605.15824 • Published 6 days ago • 54
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published 17 days ago • 332
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published Apr 13 • 143