The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 11 days ago • 397
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 12 days ago • 341
Show-Harness: Just a VLM Agent Can Play Robots Paper • 2609.10522 • Published about 1 month ago • 144