Author

Jun-Hao He

h-index 2 View on Semantic Scholar

We have 2 of 12 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 Sep 2026

NebulaSD: Many-for-Many Speculative Decoding

Speculative decoding accelerates Large Language Model (LLM) inference by using a lightweight draft model to propose candidate tokens for parallel verification by a target model. Drafting and verification, however, exhibit different service characteristics and favor different batch configurations, making fixed draft-tar...

Jun-Hao He, Hong-Yang Du · 0 citations

#natural language process... Preprint Aug 2026

CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation

On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with unequal supervision value. Selective OPD addresses this limitation by allocating supervision non-uniformly across response tokens according to their estimate...

Enhan Li, Jun-Hao He, Hong-Yang Du · 4 citations