The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
Sophia Torres
atltorres
·
AI & ML interests
ML in healthcare — yes, it's as hard as it sounds
Recent Activity
upvoted a paper about 1 month ago
VisionHOPE: Visual Backbones as Self-Modifying Learning Systems updated a model about 2 months ago
atltorres/visual-question-answeringOrganizations
None yet