Mingzhi Hu
Staff Research Scientist
Research areas: Large language models, machine learning, feature engineering, data mining
Biography
Mingzhi Hu is a Staff Research Scientist at Visa Research. Before joining Visa Research, Mingzhi received her Ph.D. in Data Science from Worcester Polytechnic Institute, where she was advised by Prof. Yanhua Li. Her doctoral research focused on foundation-model-style learning for spatial-temporal data. She also holds an M.S. in Applied Statistics from Syracuse University and a B.S. in Applied Mathematics from Dalian University of Technology.
At Visa Research, Mingzhi works on AI and machine learning methods for real-world financial and payment-related applications. Her recent work explores agentic coding, LLM-based automated feature engineering and transaction foundational models. Mingzhi has published research in leading venues including KDD, ACL, ICDM, SDM, ACM SIGSPATIAL, and TMLR. Her publications cover foundational models of transaction data, applications of Large Language models, spatial-temporal data mining, and trustworthy evaluation of LLM-generated data.
Publications
- Yingtong Dou, Zhimeng Jiang, Tianyi Zhang, Mingzhi Hu, Zhichao Xu, Shubham Jain, Uday Singh Saini, Xiran Fan, Jiarui Sun, Menghai Pan, Junpeng Wang, Xin Dai, Liang Wang, Chin-Chia Michael Yeh, Yujie Fan, Yan Zheng, Vineeth Rakesh, Huiyuan Chen, Guanchu Wang, Mangesh Bendre, Zhongfang Zhuang, Xiaoting Li, Prince Aboagye, Vivian Lai, Minghua Xu, Hao Yang, Yiwei Cai, Mahashweta Das, Yuzhong Chen. “TransactionGPT” Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining ADS track, 2026
- Kaituo Zhang, Mingzhi Hu, Hoang Anh Duy Le, Fariha Kabir Torsha, Zhimeng Jiang, Minh Khai Bui, Chia-Yuan Chang, Yu-Neng Chuang, Zhen Xiong, Ying Lin, Guanchu Wang, and Na Zou. “A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data.” Published in Transactions on Machine Learning Research, 2026.
- Mingzhi Hu, Xin Zhang, Yanhua Li, and Jun Luo. “KG-STFT: Knowledge Graph-Guided Human-Generated Spatial-Temporal Cross-task Fine-Tuning.” Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems, 2025.
- Chia-Yuan Chang, Zhimeng Jiang, Vineeth Rakesh, Menghai Pan, Chin-Chia Michael Yeh, Guanchu Wang, Mingzhi Hu, Zhichao Xu, Yan Zheng, Mahashweta Das, and Na Zou. “MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation.” The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025).
- Mingzhi Hu, Xin Zhang, Yanhua Li, Yiqun Xie, Xiaowei Jia, Xun Zhou, and Jun Luo. “Only Attending What Matter within Trajectories: Memory-Efficient Trajectory Attention.” Proceedings of the 2024 SIAM International Conference on Data Mining (SDM).
- Mingzhi Hu, Zhuoyun Zhong, Xin Zhang, Yanhua Li, Yiqun Xie, Xiaowei Jia, Xun Zhou, and Jun Luo. “Self-supervised Pre-training for Robust and Generic Spatial-Temporal Representations.” 2023 IEEE International Conference on Data Mining (ICDM).
- Mingzhi Hu, Xin Zhang, Yanhua Li, Xun Zhou, and Jun Luo. “ST-iFGSM: Enhancing Robustness of Human Mobility Signature Identification Model via Spatial-Temporal Iterative FGSM.” Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023.