The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation Paper • 2609.36484 • Published 14 days ago • 556
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems Paper • 2609.33325 • Published 16 days ago • 342
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation Paper • 2609.08798 • Published Sep 8 • 83