The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
Elif Mateusz Andersson
julesbir
GABRIELSANTOSner's profile picture
webbrain-one-799765's profile picture
webbrain-one-547331's profile picture·
AI & ML interests
Data, models, and a bit of chaos.
Recent Activity
updated a dataset about 1 month ago
julesbir/medical-corpus published a dataset about 1 month ago
julesbir/medical-corpus updated a model about 1 month ago
julesbir/multitask-baselineOrganizations
None yet
upvoted 2
papers about 1 month ago
upvoted 3
papers 3 months ago