Skip to content

Author

N. Sadagopan

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Token Utility for On-Policy Distillation via Local Trust-Region Optimization

Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-student disagreement, and mismatch direction. We instead derive token importance from the distillation objective itself: how much can each position's loss decrease under an...

N. Sadagopan, Yilan Chen, Vijay Lingam · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.