Steering the Teacher: Improving On-Policy Self-Distillation for Thinking Models
Paper • 2610.34005 • Published • 3
Hanyang Chen
hanyang-chen
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Steering the Teacher: Improving On-Policy Self-Distillation for Thinking Models liked a model 6 months ago
2toINF/X-VLA-RoboTwin2 liked a model 6 months ago
motus-robotics/pi0.5_robotwin2Organizations
None yet
upvoted a paper 1 day ago