Xiaohan Qin

works on

efficient training 1 large language models 1 residual stream expansion 1 sparse computation 1 transformer architectures 1

From the 1 of 8 linked papers with an AI index.

collaborators

Showing cs.AIShow all

1 paper · 1 filter

cs.AI2025

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

Xiaohan Qin, Xiaoxing Wang, Ning Liao +5

Data quality plays a critical role in enhancing supervised fine-tuning (SFT) for large language models (LLMs), and token-level data selection has emerged as a promising direction f…