The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 553
이지우
doyunkang
·
AI & ML interests
Building AI products for the enterprise
Recent Activity
updated a model 5 days ago
doyunkang/mixer-checkpoint published a model 5 days ago
doyunkang/mixer-checkpoint liked a model 5 days ago
autotrust/JEV-27B-VLOrganizations
None yet