The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 419
Anderson
andersonoao
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks upvoted a paper 3 days ago
MaLiang-Harness: A Programmable Path to Image and Video GenerationOrganizations
None yet