The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 580
संजय शर्मा
rwchauhan
AI & ML interests
Exploring deep learning, computer vision and LLMs.
Recent Activity
updated a model 6 days ago
rwchauhan/3d-scene-understanding-exp published a model 6 days ago
rwchauhan/3d-scene-understanding-expOrganizations
None yet