The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 553
Minho
malim1994
·
AI & ML interests
CS @ TU Munich. Looking for internships.
Recent Activity
updated a dataset 5 days ago
malim1994/finance-collection published a dataset 5 days ago
malim1994/finance-collection liked a dataset 5 days ago
SwayStar123/preprocessed_commoncatalog-cc-byOrganizations
None yet
upvoted 2
papers 8 days ago