The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 581
Davi Silva
davisilvaso
·
AI & ML interests
None yet
Recent Activity
liked a dataset 1 day ago
genrobot2025/Gen-HumanEgo liked a model 1 day ago
autotrust/JEV-27B-VL updated a dataset 6 days ago
davisilvaso/sensor-fusion-samplesOrganizations
None yet
upvoted a paper 6 days ago