The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 558
Andriy Polishchuk
andriypz
·
AI & ML interests
Learning ML every day. Love open source and cool models.
Recent Activity
liked a dataset 8 days ago
mou3az/Question-Answering-Generation-Choices liked a model 8 days ago
autotrust/JEV-27B-VLOrganizations
None yet