The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 553
Adam Smith
brssmith
·
AI & ML interests
None yet
Recent Activity
liked a model 4 days ago
autotrust/JEV-27B-VL updated a dataset 10 days ago
brssmith/legal-dataset published a dataset 10 days ago
brssmith/legal-datasetOrganizations
None yet