Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published 11 days ago • 690
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published Aug 15 • 447
VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation Paper • 2605.16079 • Published May 15 • 28
MolmoAct2: Action Reasoning Models for Real-world Deployment Paper • 2605.02881 • Published May 4 • 356
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents Paper • 2604.11784 • Published Apr 13 • 143