The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 553
Austin Taylor
jadomingo05
·
AI & ML interests
Pizza is my favorite algorithm
Recent Activity
liked a model 4 days ago
autotrust/JEV-27B-VL liked a Space 9 days ago
ADRXtractor/ADR_XtractorOrganizations
None yet