Assistant Professor
School of Software, Zhejiang University, China
Email: tangxiu@zju.edu.cn / Google Scholar

My research interests lie generally in the area of AI & DB, software testing, multi-modal learning.

News

I am currently looking for PhD students to work on AI & DB. Please email me your CV if you are interested.

PAPERS

AI & DB

• Xu Gao, Xiu Tang^*, Chang Yao, Sai Wu, Gongsheng Yuan, Wenchao Zhou, Feifei Li, Gang Chen.
  OMCR: An Online Multivariate Forecaster for Cloud Resource Management.
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025.

• Sai Wu, Ruichen Xia, Dingyu Yang, Rui Wang, Huihang Lai, Jiarui Guan, Jiameng Bai, Dongxiang Zhang, Xiu Tang, Zhongle Xie, Peng Lu, Gang Chen.
  MorphingDB: A Task-Centric AI-Native DBMS for Model Management and Inference.
  The ACM Special Interest Group on Management of Data (SIGMOD), 2026.

• Xiu Tang, Shijie Yang, Sai Wu, Dongxiang Zhang, Wenchao Zhou, Feifei Li, Gang Chen.
  Unveiling Logic Bugs in SPJG Query Optimizations within DBMS.
  ACM Transactions on Database Systems (TODS), 2025.

• Xuhang Zhu, Xiu Tang^*, Sai Wu, Jichen Li, Haobo Wang, Chang Yao, Quanqing Xu, Gang Chen.
  CoLA: Model Collaboration for Log-based Anomaly Detection.
  International Conference on Very Large Data Bases (VLDB), 2025. VLDBJ "Best of VLDB 2025" Special Issue (Invited)

• Wenhao Liu, Xiu Tang^*, Sai Wu, Chang Yao, Gongsheng Yuan, Gang Chen.
  A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code.
  International Conference on Very Large Data Bases (VLDB), 2025.

• Xiu Tang, Wenhao Liu, Sai Wu, Chang Yao, Gongsheng Yuan, Shanshan Ying, Gang Chen.
  QueryArtisan: Generating Data Manipulation Codes for Ad-hoc Analysis in Data Lakes.
  International Conference on Very Large Data Bases (VLDB), 2025.

• Jiani Yang, Sai Wu, Yong Wang, Dongxiang Zhang, Yifei Liu, Xiu Tang, Gang Chen.
  Twisted Twin: A Collaborative and Competitive Memory Management Approach in HTAP Systems.
  International Conference on Very Large Data Bases (VLDB), 2025.

• Haitian Hang, Xiu Tang, Jianling Sun, Lingfeng Bao, David Lo, Haoye Wang.
  Robust Auto-Scaling with Probabilistic Workload Forecasting for Cloud Databases.
  IEEE International Conference on Data Engineering (ICDE), 2024.

• Xiu Tang, Sai Wu, Dongxiang Zhang, Ziyue Wang, Gongsheng Yuan, Gang Chen.
  A Demonstration of DLBD: Database Logic Bug Detection System.
  International Conference on Very Large Data Bases (VLDB), 2023.

• Xiu Tang, Sai Wu, Dongxiang Zhang, Feifei Li, Gang Chen.
  Detecting Logic Bugs of Join Optimizations in DBMS.
  The ACM Special Interest Group on Management of Data (SIGMOD), 2023. ACM SIGMOD 2023 Best Paper Award

• Xiu Tang, Sai Wu, Mingli Song, Shanshan Ying, Feifei Li, Gang Chen.
  PreQR: Pre-training Representation for SQL Understanding.
  The ACM Special Interest Group on Management of Data (SIGMOD), 2022.

• Xiu Tang, Sai Wu, Gang Chen, Jinyang Gao, Wei Cao, Zhifei Pang.
  A Learning to Tune Framework for LSH.
  International Conference on Data Engineering (ICDE), 2021.

• Zhen Zhu, Yibo Wang, Shouqing Yang, Lin Long, Runze Wu, Xiu Tang, Junbo Zhao, Haobo Wang.
  CORAL: Collaborative Automatic Labeling System based on Large Language Models.
  International Conference on Very Large Data Bases (VLDB), 2024.

• Zhou He, Zhifei Pang, Xiu Tang, Sai Wu, Gang Chen.
  Corpus-Centric Learning for Zero-Shot Table.
  THE 49th international ACM SIGIR conference on research and development in information retrieval (SIGIR), 2026.

• Zhihao Chang, Ding Wang, Xiu Tang^*, Kingsum Chow and Jianwei Yin.
  General Neural Embedding for Sequence Distance Approximation.
  THE 48th international ACM SIGIR conference on research and development in information retrieval (SIGIR), 2025.

• Hongwei Yuan, Xiu Tang, Ke Chen, Lidan Shou, Gang Chen, Huan Li.
  CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation.
  The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025.

• Haitian Hang, Xiu Tang, Bo Zhu, Jianlin Sun.
  Unlocking the Power of Diversity in Index Tuning for Cluster Databases.
  International Conference on Database and Expert Systems Applications (DEXA), 2024.

Multimodal Learning & NLP

• Kunyi Li, Sai Wu, Xiu Tang^*, Chang Yao, Songhao Bu, Quanqing Xu, Gang Chen.
  Debugging Engine Enhanced by Prior Knowledge: Can We Teach LLM How to Debug?
  The ACM International Conference on the Foundations of Software Engineering (FSE), 2026.

• Qianyi Yang, Bingcang Huang, Qin Zhou, Zhe Wang, Kai Chen, Xiu Tang, Chang Yao, Sai Wu.
  Unsupervised Brain Anomaly Detection Using Structure-Preserving Noise Generation and Multi-Scale Dual-Expert Ensembles.
  IEEE Journal of Biomedical and Health Informatics, 2026.

• Zhenlong Dai, Zhuoluo Zhao, Hengning Wang, Xiu Tang, Sai Wu, Chang Yao, Zhipeng Gao, Jingyuan Chen.
  Learner-Tailored Program Repair: A Solution Generator with Iterative Edit-Driven Retrieval Enhancement.
  The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.

• Han Lin, Xiu Tang^*, Huan Li, Wenxue Cao, Sai Wu, Chang Yao, Lidan Shou, Gang Chen.
  T2DR: A Two-Tier Deficiency-Resistant Framework for Incomplete Multimodal Learning.
  The 63rd Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025.

• Zhenlong Dai, Bingrui Chen, Zhuoluo Zhao, Xiu Tang, Sai Wu, Chang Yao, Zhipeng Gao, Jingyuan Chen.
  Less is More: Adaptive Program Repair with Bug Localization and Preference Learning.
  The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025.

• Xuhang Zhu, Xiu Tang, Sai Wu, Yixuan Tang, Haobo Wang, Chang Yao, Ruichen Xia, Gang Chen.
  Bridge-SQL: Bridging Single- and Multi-Turn Text-to-SQL via Preference-Aligned Question Rewriting.
  The 31st International Conference on Database Systems for Advanced Applications (DASFAA), 2026.

• Lilong Wen, Xiu Tang, Dongxiang Zhang.
  TWIST: Text-only Weakly Supervised Scene Text Spotting Using Pseudo Labels.
  International Conference on Multimedia Retrieval (ICMR), 2024.

• Xiu Tang, Sai Wu, Gang Chen, Ke Chen, Lidan Shou.
  Learning to Label with Active Learning and Reinforcement Learning.
  Database Systems for Advanced Applications (DASFAA), 2021.

• Xiu Tang, Yangchao Xu, Xuefeng Lu, Qiang He, Jun Fang, Junjie Chen.
  DeMRC: Dynamically Enhanced Multi-hop Reading Comprehension Model for Low Data.
  Advanced Data Mining and Applications (ADMA), 2022.

• Ce Xu, Xiu Tang, Peng Lu.
  Using the Strongest Adversarial Example to Alleviate Robust Overfitting.
  Advanced Data Mining and Applications (ADMA), 2022.

STUDENTS

Wenhao Liu, PhD, started in 2023, AntGroup.
Xu Gao, PhD, started in 2023.
Kunyi Li, PhD, started in 2023, Tencent.
Xuhang Zhu, PhD, started in 2024, AntGroup.
Kedi Wang, PhD, started in 2024, AntGroup.
Zhensheng Luo, PhD, started in 2025.

Jichen Li, Master, started in 2024
Wenxue Cao, Master, started in 2024, AntGroup.
Jianhao Shao, Master, started in 2024
Peiqi Luo, Master, started in 2024
Zhiqiang Cheng, Master, started in 2025
Kaixin Jin, Master, started in 2025
Zheng Meng, Master, started in 2025
Yitong Zhang, Master, started in 2025
Jinjin Wang, Master, started in 2025

Han Lin, Master, graduated in 2026, Alibaba.
Yuanrong Wu, Master, graduated in 2026, Baidu.
Xingjian Huang, Master, graduated in 2026, Tencent.
Mengfei Cai, Master, graduated in 2026, AntGroup.
Shijie Yang, Master, graduated in 2025, Tencent.

EDUCATION

• PhD in Computer Science and Technology. Zhejiang University, Hangzhou, China (Mar. 2023)
  Advisor: Prof. Sai Wu

TEACHING

• Advanced Database Technology, 2025 Autumn
• Software Testing, 2025 Winter
• Advanced Database Technology, 2024 Autumn
• Software Testing, 2024 Winter

Program Committee Member (Reviewer):

IEEE’s Transactions on Computers (IEEE TC) 2025
Transactions on Knowledge and Data Engineering (TKDE) 2024
ACM Multimedia (MM) 2026
AAAI Conference on Artificial Intelligence (AAAI) 2026
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2026
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2026
DBTest@SIGMOD 2024, 2026
The Conference on Information and Knowledge Management (CIKM) 2024, 2025
Data Scuence and Engineering (DSE) 2024, 2025
Knowledge and Information Systems (KAIS) 2025