MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 4 days ago • 384
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 3 days ago • 274
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning Paper • 2608.26105 • Published Aug 26 • 191
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher Paper • 2608.26872 • Published Aug 27 • 65