Ann Arbor · 2025

Xingjian Zhang张行健

I build and evaluate AI that reasons over hard-to-verify tasks.

— research.focus

3 threads

>Quantitative evaluation of AI systems' innovative ability.
>Reasoning capabilities of AI in non-standard tasks.
>AI agents that automate scientific research workflows (computer science, neuroscience, behavioral science).

— publications[selected]

2026

TMLR

Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters

Xingjian Zhang, Tianhong Gao, Suliang Jin, Tianhao Wang, Teng Ye, Eytan Adar, Qiaozhu Mei

paper code

2025

KDD

MapExplorer: New Content Generation from Low-Dimensional Visualizations

Xingjian Zhang, Ziyang Xiong, Shixuan Liu, Yutong Xie, Tolga Ergen, Dongsub Shim, Hua Xu, Honglak Lee, Qiaozhu Mei

paper code

2025

NAACL

MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows

Xingjian Zhang*, Yutong Xie*, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, and others

paper code

2024

TMLR

Can LLMs Effectively Leverage Graph Structural Information: When and Why

Jin Huang, Xingjian Zhang, Qiaozhu Mei, Jiaqi Ma

paper code

— news[latest]