WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution Paper • 2610.18067 • Published Oct 13 • 28
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published Oct 8 • 42
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published Sep 28 • 80
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation Paper • 2609.11638 • Published Sep 10 • 220
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation Paper • 2609.03756 • Published Sep 3 • 17