Bojie Hu

Papers on Lattice

Total citations

Topics

h-index

Research focus

Inference & Quantization (1)Natural Language Processing (1)RLHF & Preference Learning (1)

Frequent co-authors

Songming Zhang (1)Xue Zhang (1)Tong Zhang (1)Yufeng Chen (1)

Papers (1)

Mar 4, 2025

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation

Token-level alignment, powered by a novel distillation approach, lets LLMs learn faster and better by avoiding the pitfalls of response-level reward optimization.

Songming Zhang, Xue Zhang, Tong Zhang +35

Inference & Quantization Natural Language Processing RLHF & Preference Learning

Search

Bojie Hu

Research focus

Frequent co-authors

Papers (1)