The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 564
Nathan Leroy
nqleroy40
·
AI & ML interests
None yet
Recent Activity
updated a dataset 15 days ago
nqleroy40/gaming-image-depth-benchmark published a dataset 15 days ago
nqleroy40/gaming-image-depth-benchmark updated a dataset 15 days ago
nqleroy40/social-datasetOrganizations
None yet