Who am I?
Hi, I’m Zhongwei, a PhD student in the Computer Science and Engineering Division at the University of Michigan, Ann Arbor. I’m fortunate to be advised by Prof.Lin Ma. My research interests broadly span the intersection of AI and systems. Currently, I’m working on cost optimization for LLM agents. I’m also very interested in building and optimizing data pipelines for robotics.
Previously, I worked on optimizing data lakehouse systems (LakeHelm) and on GPU databases.
Before that, I obtained my B.S from Xi’an Jiaotong University, where I majored in computer science.
Publications
- LakeHelm: Zero-Shot Lakehouse Advisor for Joint Engine-Format Selection and Configuration
Zhongwei Xu, Siyuan Dong, Haotian Gong, Donna Pham, Lin Ma
PVLDB 19(8), 2026 [Paper] - Evaluating Non-AI Experts’ Interaction with AI: A Case Study in Library Context
Qingxiao Zheng, Minrui Chen, Hyanghee Park, Zhongwei Xu, Yun Huang
CHI 2025 [Paper] - Systematically Detecting Packet Validation Vulnerabilities in Embedded Network Stacks
Paschal C. Amusuo, Ricardo Andrés Calvo Méndez, Zhongwei Xu, Aravind Machiry, James C. Davis
ASE 2023 [Paper] - Synergizing Human-AI Agency: A Guide of 23 Heuristics for Service Co-Creation with LLM-based Agents
Qingxiao Zheng, Zhongwei Xu, Abhinav Choudhry, Yuting Chen, Yongming Li, Yun Huang
arXiv preprint, 2023 [Paper]