The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 564
윤예준
tbcampbell
·
AI & ML interests
Exploring the open AI ecosystem.
Recent Activity
upvoted a paper 7 days ago
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems updated a model 15 days ago
tbcampbell/contrastive-large-2024Organizations
None yet
upvoted 2
papers 7 days ago