I am a Distinguished Professor (特聘研究员) at the School of Computer Science and Technology, Hangzhou Dianzi University (HDU). I received Ph.D. degree in Computer Science and Technology from Zhejiang University (ZJU) in 2026, advised by Prof. Yunjun Gao. My research interests lie in context data management for LLM agents.
Please don’t hesitate to reach out to me if you are interested in a discussion or collaboration.
I am actively looking for self-motivated students (undergraduate/graduate/phd student) who are interested in vector databases, agent memory, and LLM inference. Feel free to reach out via email (wmzssy@hdu.edu.cn).
Research topics:
- Vector Databases (Algorithms, Systems, etc.)
- Context Databases (RAG, Agent Memory, Multi-Modal, etc.)
- LLM Inference (Compute/Hardware Acceleration, Quantization, etc.)
News
- [Mar. 2026]: I successfully earned my Ph.D. degree.
- [Mar. 2026]: Our work on Hybrid Search Systems has been accepted to VLDB 2026.
- [Mar. 2026]: Our work on Hubness Analysis for Graph-based Vector Search has been accepted to SIGMOD 2026.
- [Jan. 2026]: Our work on Multi-Vector Search has been accepted to SCIS 2026.
- [Nov. 2025]: Our work on Out-Of-Distribution (OOD) Vector Search was accepted to SIGMOD 2026.
- [Dec. 2025]: I am honored to be recognized as a Top Reviewer for NeurIPS 2025.
- [Jul. 2025]: Our paper (VLDB 2021) was included in 2025 Highly-Cited List (Google Scholar).
- [Jan. 2025]: Our work on Graph Indexing Acceleration for Vector Search was accepted to SIGMOD 2025.
- [Jan. 2025]: I was selected for the China Association for Science and Technology (CAST) Youth Talent Support Program for Ph.D. Students.
- [Dec. 2024]: I am honored to receive the ByteDance Scholarship.
- [May 2024]: I am honored to receive the ACM SIGMOD Student Travel Award.
- [May 2024]: Our work on Multi-modal QA Systems was accepted to VLDB 2024.
- [May 2024]: Our work on Multi-modal Retrieval was accepted to ICDE 2024.
- [Nov. 2023]: Our work on On-Disk Vector Search Optimization (Starling) was accepted to SIGMOD 2024.
- [Nov. 2023]: Our work on Multi-modal Retrieval was accepted to ICDE 2024.
- [Sep. 2023]: Our work on Vector Search with Attribute Constraints was accepted to NeurIPS 2023.
Scroll to see more
Publications
2026
-
VLDB’26 Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Search
Mengzhao Wang, Boyu Tan, *Yunjun Gao, Hai Jin, Yingfeng Zhang, Xiangyu Ke, Xiaoliang Xu, Yifan Zhu
52nd International Conference on Very Large Data (VLDB), BasesBoston, MA, USA, Aug 31st-Sep 4th, 2026.
CCF-A, [PDF | Code], To appear in 2026. -
SIGMOD’26 Through the Lens of Hubness: A Revisit on Graph-Based Approximate Nearest Neighbor Search: [Experiments & Analysis]
Xiaoliang Xu, Haonan Dai, Can Li, *Mengzhao Wang, Qiang Yue
Proceedings of the ACM on Management of Data (SIGMOD), Bengaluru, India, May 31-June 05, 2026.
CCF-A, [PDF | Code], To appear in 2026. -
SCIS’26 Empowering High-Dimensional Multi-Vector Search
Mengzhao Wang, Xiangyu Ke, Yifan Zhu, *Yunjun Gao, Yaofeng Tu
Science China Information Sciences (SCIS), 2026.
CCF-A, [PDF | Code], To appear in 2026. -
SIGMOD’26 Efficient and Robust Out-Of-Distribution Vector Similarity Search with Cross-Distribution Monotonic Graph
^Qiang Yue, ^Mengzhao Wang, *Xiaoliang Xu, Cheng Long, Yuxiang Wang, Jiahui Wang
Proceedings of the ACM on Management of Data (SIGMOD), Bengaluru, India, May 31-June 05, 2026.
CCF-A, [PDF | Code], To appear in 2026.
2025
- SIGMOD’25 Accelerating Graph Indexing for ANNS on Modern CPUs
Mengzhao Wang, Haotian Wu, Xiangyu Ke, *Yunjun Gao, Yifan Zhu, Wenchao Zhou
Proceedings of the ACM on Management of Data (SIGMOD), Berlin, Germany, June 22-27, 2025.
CCF-A, [PDF | Code]
2024
-
SIGMOD’24 Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment
^Mengzhao Wang, ^Weizhi Xu, *Xiaomeng Yi, Songlin Wu, Zhangyang Peng, Xiangyu Ke, Yunjun Gao, *Xiaoliang Xu, Rentong Guo, Charles Xie
Proceedings of the ACM on Management of Data (SIGMOD), Santiago, Chile, June 9-14, 2024.
CCF-A, [PDF | Code] -
VLDB’24 An Interactive Multi-modal Query Answering System with Retrieval-Augmented Large Language Models
Mengzhao Wang, Haotian Wu, Xiangyu Ke, *Yunjun Gao, Xiaoliang Xu, Lu Chen
50th International Conference on Very Large Databases (VLDB), Guangzhou, China, August 26-30, 2024.
CCF-A, [PDF | Code | Video] -
ICDE’24 MUST: An Effective and Scalable Framework for Multimodal Search of Target Modality
Mengzhao Wang, Xiangyu Ke, Xiaoliang Xu, *Lu Chen, Yunjun Gao, Pinpin Huang, Runkai Zhu
40th IEEE International Conference on Data Engineering (ICDE), Utrecht, Netherlands, May 13-17, 2024.
CCF-A, [PDF | Code]
2023
- NeurIPS’24 An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint
Mengzhao Wang, Lingwei Lv, *Xiaoliang Xu, Yuxiang Wang, Qiang Yue, Jiongkang Ni
The Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, USA, Dec 10-16, 2024.
CCF-A, [PDF | Code]
2021
-
VLDB’21 A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search
Mengzhao Wang, Xiaoliang Xu, Qiang Yue, *Yuxiang Wang
47th International Conference on Very Large Databases (VLDB), Copenhagen, Denmark, August 16-20, 2021.
CCF-A, [PDF | Code] -
KBS’21 Two-Stage Routing with Optimized Guided Search and Greedy Algorithm on Proximity Graph
Xiaoliang Xu, *Mengzhao Wang, Yuxiang Wang, Dingcheng Ma
Knowledge-Based Systems (KBS), Volume 229, 11 October 2021, 107305.
CAS-Q1, Top, [PDF | Code]
Honors and Awards
- NeurIPS 2025 Top Reviewer,2025.
- ByteDance Scholarship (字节跳动奖学金,全球15人), 2024.
- Youth Talent Support Program for Ph.D. Students (首届中国科协青年人才托举工程博士生专项计划), 2024.
- National Scholarship of China (国家奖学金), 2021, 2024.
- SIGMOD Student Travel Award, 2024.
- SIGMOD Student Programming Contest Finalist, 2024.
- Outstanding Master’s Thesis of Zhejiang Province (浙江省优秀硕士学位论文), 2023.
- Outstanding Graduate of Zhejiang Province (浙江省优秀毕业生), 2022, 2026.
Educations
- 2022.09 - 2026.03, Ph.D., Zhejiang University. Supervisor: Prof. Yunjun Gao (高云君), Prof. Xiangyu Ke (柯翔宇), and Prof. Lu Chen (陈璐).
- 2019.09 - 2022.03, M.E., Hangzhou Dianzi University. Supervisor: Prof. Xiaoliang Xu (徐小良) and Prof. Yuxiang Wang (王宇翔).
- 2015.09 - 2019.06, B.E., Qingdao University of Science and Technology.
Invited Talks
- Large-Scale Vector Data Management Technology, Wuhan Dameng Database Co., Ltd., 2024.11.
- Graph-Based Vector Search: Index Layout and Search Optimizations on Disk, ByteDance, 2024.08.
- Vector Similarity Search: Disk-Based Graph Index Layout and Search Optimizations, Huawei (Data Storage Technology Planning Dept, Nanjing), 2024.08.
- Vector Databases: Index Layout and Search Optimizations on SSD, Baidu, 2024.06.
- High-Dimensional Vector Similarity Search, Huawei (Hangzhou Research Inst.), 2023.12.
- Approximate Nearest Neighbor Search with Attribute Constraint, Huawei (MRC, Germany), 2023.11.
- Research on Large-Scale High-Dimensional Vector Processing, Alibaba DAMO Academy, 2023.11.
- Graph-Based Multi-Vector Search and GPU Acceleration, Datawhale, 2023.03.
- Graph-Based Approximate Nearest Neighbor Search: An Experimental Study, Zilliz, 2021.09.
Internships
- 2025.04 - 2026.03: Intern, Recommendation System Architect, ByteDance.
- 2022.05 - 2022.08: Intern, Research Engineer, Zilliz.
- 2021.09 - 2022.04: Intern, R&D Engineer, Zhejiang Lab.
Contact
- Email: wmzssy@hdu.edu.cn / wmengzhao@qq.com
- WeChat ID (微信): wy156646264
- Address: Room 401, Building 1, Xiasha Campus, Hangzhou Dianzi University