The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 580
C. Yang
Chaotyang
·
AI & ML interests
Rock climber. Also writes code.
Recent Activity
upvoted a paper 8 days ago
In-Context Learning for Robots: Methods and Applications upvoted a paper 8 days ago
VisionHOPE: Visual Backbones as Self-Modifying Learning SystemsOrganizations
None yet