The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 179
Qiang Chen
qichen1989
·
AI & ML interests
Exploring deep learning, computer vision and LLMs.
Recent Activity
updated a dataset 15 days ago
qichen1989/wildlife-corpus published a dataset 15 days ago
qichen1989/wildlife-corpusOrganizations
None yet