The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 301
Stephanie Rodriguez
stephanierodriguez
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 20 hours ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search AgentsOrganizations
None yet
upvoted 2
papers about 20 hours ago