Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 235
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 • 107
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources Paper • 2606.29538 • Published Jul 16 • 91
SkillOpt: Executive Strategy for Self-Evolving Agent Skills Paper • 2605.23904 • Published May 22 • 220
FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization Paper • 2605.15824 • Published May 15 • 32