The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 556
नेहा नायर
saanviverma
AI & ML interests
Exploring deep learning, computer vision and LLMs.
Recent Activity
updated a model 12 days ago
saanviverma/project-multitask published a model 12 days ago
saanviverma/project-multitaskOrganizations
None yet