I received my Ph.D in database group of Tsinghua University, under the supervision of professor Guoliang Li.I received my bachelor degree in Computer Science of BUPT. I am interested in Distributed System, Similarity Search and Machine Learning for Query Optimization.

[Google Scholar] [Github]

Work Experience

• 2021.07 - present Researcher at Huawei, Haidian, Beijing
  Works on build-in AI for openGauss/GaussDB (VectorDB, AI-based Optimizer, LLM, NewHardware)
• 2017.11 - 2018.05 Research Asistant of CSAIL, MIT, Boston, MA
  Works on end-to-end entity consolidation framework

Researches

• GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications.
  Guoliang Li, Ji Sun, James Jie Pan, Jiang Wang, Yongqing Xie, Ruicheng Liu, Wen Nie
  [Full(VLDB2025)]

• Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph.
  Hongya Wang, WenLong Wu, Cong Luo, Aobei Bian, Chunguang Meng, Yishuo Wu, Ji Sun
  [Full(ICDE2025)]

• GaussML: An End-to-End In-Database Machine Learning System.
  Guoliang Li, Ji Sun, Lijie Xu, Shifu Li, Jiang Wang, Wen Nie
  [Full(ICDE2024)] [Slide]

• Learned Cardinality Estimation: A Design Space Exploration and a Comparative Evaluation.
  Ji Sun, Jintao Zhang, Zhaoyan Sun, Guoliang Li, Nan Tang
  [Code] [E&A(VLDB2022)] [Slide]

• DBMind: A Self-Driving Platform in openGauss.
  Xuanhe Zhou,Lianyuan Jin,Ji Sun,Xinyang Zhao,et al.
  [Demo(VLDB2021)]

• openGauss: An Autonomous Database System.
  Guoliang Li,Xuanhe Zhou,Ji Sun,Xiang Yu,et al.
  [Full Industry(VLDB2021)]

• Learned Cardinality Estimation for Similarity Queries.
  Ji Sun, Guoliang Li, Nan Tang
  [Full Research(SIGMOD2021)] [Slides]

• An Autonomous Materialized View Management System with Deep Reinforcement Learning.
  Yue Han, Guoliang Li, Haitao Yuan, Ji Sun
  [Short (ICDE2021)]

• Query Performance Prediction for Concurrent Queries using Graph Embedding.
  Xuanhe Zhou, Ji Sun, Guoliang Li, Jianhua Feng
  [Full Research(VLDB2020)]

• Automatic View Generation with Deep Learning and Reinforcement Learning.
  Haitao Yuan, Guoliang Li, Ling Feng, Ji Sun, Yue Han
  [Full Research(ICDE2020)]

• An End-to-End Learning-based Cost Estimator.
  Ji Sun, Guoliang Li
  [Code] [Full Research(VLDB2020)][slide]

• Database Meets Artificial Intelligence: A Survey.
  Xuanhe Zhou, Chengliang Chai, Guoliang Li, Ji Sun
  [Full Research(TKDE2020)]

• Hybrid Entity Resolution Approach for E-commerce Products.
  Ji Sun, Guoliang Li
  [Code] [Poster(Sigmod2020)]

• Optimizing Human Involvement for Entity Matching and Entity Consolidation.
  Ji Sun, Dong Deng, Ihab Ilyas, Guoliang Li, Samuel Madden, Mourad Ouzzani, Michael Stonebraker, Nan Tang
  [Technical Report]

• Dima: Distributed In-memory Similarity-based Query Processing System.
  Ji Sun, Zeyuan Shang, Guoliang Li, Dong Deng, Zhifeng Bao
  [Code] [Video] [Demo(VLDB2017)] [Full Research(VLDB2019)]

Selected Awards

• Excellent Doctoral Dissertation Award, China Computer Federation(CCF), 2021
• Outstanding Graduate of Beijing, Beijing Gov., 2021
• Outstabding Graduate, Department of Computer Science of Tsinghua, 2021
• 84 Future Innovation Scholarship, Tsinghua University, 2020
• Xiaomi Scholarship, Tsinghua University, 2020
• ACM Sigmod Programming Contest Finalist, SIGMOD, 2020
• Student Travel Award, VLDB, 2019
• Mei Yiqi Scholarship, Tsinghua University, 2017, 2019
• Outstanding Graduate of Beijing, Beijing Gov., 2016
• First Prize Scholarship, BUPT, 2014 & 2015
• National Scholarship, Ministry of Education, 2013

Talks

• What Do We Really Need for Vector Database [CloudDB Workshop @ VLDB2024][Slides]

Services

• Committee Member of pVLDB Reproducibility
• Review of ACM TODS
• Review of JCST

---