Zongxian Yang

Zongxian Yang

Research Assistant at the HANI Lab, working on LLM reasoning, medical AI, and multimodal reasoning.

QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized Model

Published in arXiv preprint, 2025

QM-ToT explores how to preserve and improve medical reasoning performance when models are quantized or deployed under limited compute. I contributed to problem formulation, framework design, experimentation, and paper writing.