The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 397
Arthur
goncalvesarthur
·
AI & ML interests
Learning ML every day. Love open source and cool models.
Recent Activity
upvoted a paper 10 days ago
MaLiang-Harness: A Programmable Path to Image and Video Generation updated a model 25 days ago
goncalvesarthur/flamingo-demoOrganizations
None yet