The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 548
Ryan Tanaka
ryantanakawyn
·
AI & ML interests
Reinforcement learning is my therapy
Recent Activity
updated a model 9 days ago
ryantanakawyn/review-data-efficient-learning5 published a model 9 days ago
ryantanakawyn/review-data-efficient-learning5Organizations
None yet
upvoted 2
papers 9 days ago