The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 490
Hugo K. Garcia
hugarcia95
·
AI & ML interests
Learning ML every day. Love open source and cool models.
Recent Activity
updated a model 10 days ago
hugarcia95/study-neural-architecture-search published a model 10 days ago
hugarcia95/study-neural-architecture-searchOrganizations
None yet
upvoted 2
papers 10 days ago