Ziqi Chen

Expand the edge of my life

I am Ziqi (Adam) Chen, a senior undergraduate student in the School of Data Science at The Chinese University of Hong Kong, Shenzhen, pursuing a B.E. in Computer Science and Engineering.

I am fortunate to conduct research with Prof. Hongyuan Zha and Prof. Benyou Wang at CUHK-Shenzhen. Currently, I am doing research with Prof. Kexin Pei and Prof. Tian Li at UChicago.

My research interests center on efficient and adaptive LLMs, particularly in adaptive computation, self-evolving agents, and efficient reasoning. I am also interested in applying these techniques to AI for Science, especially scientific reasoning and software.

See my research and publications for more.

news

Apr 16, 2026	Started research internship in UChicago.
Mar 02, 2026	Received the Undergraduate Research Award at CUHK-Shenzhen.

selected publications

DocMaster: A Hierarchical Structure-Aware System for Document Analysis

Ziqi Chen, Yingli Zhou, Fangyuan Zhang, and 3 more authors

arXiv preprint arXiv:2607.08539, Jul 2026

Abs arXiv Bib HTML

Large language models struggle to analyze complex documents such as academic papers and financial reports because existing approaches flatten documents into plain text, discarding structural information. DocMaster parses documents into hierarchical document trees that preserve original layouts and constructs a structure-aware semantic index enabling accurate document filtering and in-depth analysis, with an interactive interface for uploading document collections, building semantic indices, filtering via natural-language queries, and question answering over filtered results.
@article{chen2026docmaster, title = {DocMaster: A Hierarchical Structure-Aware System for Document Analysis}, author = {Chen, Ziqi and Zhou, Yingli and Zhang, Fangyuan and Xu, Quanqing and Yang, Chuanhui and Fang, Yixiang}, journal = {arXiv preprint arXiv:2607.08539}, year = {2026}, month = jul, archiveprefix = {arXiv}, primaryclass = {cs.CL}, url = {https://arxiv.org/abs/2607.08539}, }