Author

Hong-Xin Wei

h-index 6 View on Semantic Scholar

We have 1 of 23 papers

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.

Preprint Aug 2026

Tail-Aware Top-$k$ On-Policy Distillation

Tail-Aware Top-$k$ OPD is proposed, a novel distillation method that restores the missing tail probability signal and better aligns the student's next-token distribution with the teacher's, preventing the increase in tail probability and entropy caused by top-$k$ normalization.

Huipeng Huang, Hong-Xin Wei · 1 citation