On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics Paper • 2609.35259 • Published 5 days ago • 130
ROWBench: Do Video Models Render What the Program Specifies? Paper • 2610.02205 • Published 2 days ago • 50
World Observer: Joint Actor-Observer Generation for Persistent World Modeling Paper • 2610.02162 • Published 2 days ago • 66