The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
Zachary P.
zacharypere
AI & ML interests
open source, computer vision, reinforcement learning, vector databases
Recent Activity
upvoted a paper 25 days ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents updated a model 27 days ago
zacharypere/multimodal-generation-analysisOrganizations
None yet