The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 549
Christopher Lopez
lopezchristopher
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 20 days ago
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks upvoted a paper 20 days ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search AgentsOrganizations
None yet
upvoted 3
papers 20 days ago