Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
Paper • 2605.26844 • Published • 25
Liu Xinhang
wenrizhou
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 days ago
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation upvoted a paper 22 days ago
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training upvoted a paper 22 days ago
Model Merging Scaling Laws in Large Language ModelsOrganizations
None yet
