The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 557
Ava Williams
ericigarcia
·
AI & ML interests
Into NLP, diffusion models and AI agents.
Recent Activity
liked a model 8 days ago
autotrust/JEV-9BOrganizations
None yet