The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 572
David Lopez
david-lopez
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
MaLiang-Harness: A Programmable Path to Image and Video GenerationOrganizations
None yet
upvoted 4
papers 5 days ago
MaLiang-Harness: A Programmable Path to Image and Video Generation
Paper • 2609.34309 • Published • 412
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 474
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 139