Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
Paper • 2605.26844 • Published • 26
xuan
Max1798
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 8 days ago
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation upvoted a paper 28 days ago
Model Merging Scaling Laws in Large Language Models upvoted a paper 28 days ago
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-TrainingOrganizations
None yet
upvoted a paper 8 days ago
upvoted 2
papers 28 days ago
liked a
model 10 months ago
updated a
model 11 months ago
published a
model 11 months ago