The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 208
خالد منصور
Omaralghamdiette
·
AI & ML interests
Exploring deep learning, computer vision and LLMs.
Recent Activity
upvoted a paper 15 days ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents updated a model about 1 month ago
Omaralghamdiette/mixer-multitask11Organizations
None yet