The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
Андрей Морозов
kmakarov
·
AI & ML interests
Interested in machine learning, NLP and open source AI.
Recent Activity
updated a model about 1 month ago
kmakarov/study-3d-scene-understanding published a model about 1 month ago
kmakarov/study-3d-scene-understandingOrganizations
None yet