The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 578
Phan Trang
vu1-984z
·
AI & ML interests
Into NLP, diffusion models and AI agents.
Recent Activity
updated a model 2 days ago
vu1-984z/lightweight-multimodal-review published a model 2 days ago
vu1-984z/lightweight-multimodal-review updated a model 2 days ago
vu1-984z/knowledge-distillationOrganizations
None yet