🧠 About Me
I am currently a Ph.D. student in the School of Information, Renmin University of China. My research focuses on graph systems, vector databases, and compression techniques, aiming to boost query performance and system throughput in resource-constrained environments through system-level optimization and efficient indexing.
🎓 Education
- Renmin University of China, Ph.D. in Computer Science
- Renmin University of China, B.Sc. in Computer Science
💼 Experience
- Beijing HaiZhi XingTu Technology Co., Ltd, Graph System Research Intern (2022.11 – 2025.2)
- SenseTime, OCR Research Intern (2020.12 – 2021.6)
📄 First-Author Publications
- VLDB 2024
Improving Graph Compression for Efficient Resource-Constrained Graph Analytics
In real-world large-scale graph processing, systems often crash or slow down due to memory overload. This work introduces a new system called Laconic, which significantly reduces memory usage while preserving query speed. It solves a real system bottleneck—handling massive graphs with limited hardware—and has already been integrated into a company’s production platform. [paper] [project page] - SIGMOD 2025
Tribase: A Vector Data Query Engine for Reliable and Lossless Pruning Compression using Triangle Inequalities
This paper focuses on speeding up search in vector databases. The system, Tribase, cuts down unnecessary computations by smartly identifying and skipping low-value data. On real-world datasets, it reduces up to 99.6% of the total computation while preserving exact accuracy, making vector search both faster and more reliable, especially under compute constraints. [paper] [project page] - SIGMOD 2026 (accepted, upcoming)
HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search
As data scales up, running vector search across many machines becomes critical. This work, Harmony, designs a distributed system that balances the workload across nodes more effectively. By reducing duplication and ensuring each machine handles a fair share of the work, it improves cost efficiency and throughput under real-world workload imbalances. [paper] [project page]
🛠️ Skill Set
- Languages: Python, C++
- Platform: Linux
- Focus: System and data processing optimization, graph/vector query engine development
🏆 Honors & Awards
- National Graduate Scholarship (2024)
- National Graduate Scholarship (2025)
📘️ Patents
- CN119759967A: ANN compression optimization for high-dimensional vectors (2nd inventor)
- CN120086218A: Sub-neighbor network vector indexing (2nd inventor)
- CN119169111A: Large-scale graph compression processing (2nd inventor)
🌍 Misc
Languages: English (CET-6)
Last updated: June 2025