孙佶｜清华大学｜学者主页

2026

Data Agents: Agentic Data Systems

Guoliang Li, Peiyao Zhou, Xuanhe Zhou, Ji Sun, Yuyu Luo, Ju Fan

IEEE Transactions on Knowledge and Data Engineering

DOI

2026

SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search

Yuchen Peng, Dingyu Yang, Zhong-Le Xie, Ji Sun, Li-Dan Shou, Ke Chen, Gang Chen

Proceedings of the VLDB Endowment

DOI

2025

GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications

Ji Sun, Guoliang Li, James Pan, Jiang Wang, Yongqing Xie, Ruicheng Liu, Wen Nie

Proceedings of the VLDB Endowment

DOI

2025

A Topology-Aware Localized Update Strategy for Graph-Based ANN Index

Song Yu, Shengyuan Lin, Shufeng Gong, Yongqing Xie, Ruicheng Liu, Yi-Jie Zhou, Ji Sun, Yanfeng Zhang, Guoliang Li, Ge Yu

Proceedings of the VLDB Endowment

DOI

2025

AgenticData: An Agentic Data Analytics System for Heterogeneous Data

Ji Sun, Guo-Liang Li, Pei-Yao Zhou, Yihui Ma, Jing-Zhe Xu, Yuan Li

arXiv.org

DOI

2025

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Yizhang Zhu, Liang-Wei Wang, Chenyu Yang, Xiao-Tian Lin, Boyan Li, Wei Zhou, Xin-Yu Liu, Zhang-Yang Peng, Tian-Qi Luo, Yu Li, Cheng-Liang Chai, Chong Chen, Shi-Min Di, Ju Fan, Ji Sun, Nan Tang, F. Tsung, Jiannan Wang, Cheng-Lin Wu, Yanwei Xu, Shao-Lei Zhang, Yong Zhang, Xuan-He Zhou, Guo-Liang Li, Yu-Yu Luo

arXiv.org

DOI

2025

Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph

Hongya Wang, Wenlong Wu, Cong Luo, Aobei Bian, Chunguang Meng, Yishu Wu, Ji Sun

IEEE International Conference on Data Engineering

DOI

2025

GaussMaster: An LLM-based Database Copilot System

Wei Zhou, Ji Sun, Xuan-He Zhou, Guoliang Li, Luyang Liu, Hao Wu, Tianyuan Wang

arXiv.org

DOI

2024

GaussML: An End-to-End In-Database Machine Learning System

Guoliang Li, Ji Sun, Li-Jie Xu, Shifu Li, Jiang Wang, Wen Nie

IEEE International Conference on Data Engineering

DOI

2023

Database Meets Artificial Intelligence: A Survey (Extended Abstract)

Xuanhe Zhou, Chengliang Chai, Guoliang Li, Ji Sun

Proceedings - International Conference on Data Engineering

DOI

2022

人在回路的数据融合系统

孙佶，李国良

《计算机学报》

2022

AutoView: An Autonomous Materialized View Management System with Encoder-Reducer

Yue Han, Guoliang Li, Haitao Yuan, Ji Sun

IEEE Transactions on Knowledge and Data Engineering

DOI

2022

AlphaQO: Robust Learned Query Optimizer

Xiang Yu, Chengliang Chai, Xinning Zhang, Nan Tang, Ji Sun, Guoliang Li

International Journal of Software and Informatics

DOI

2021

Learned cardinality estimation

Ji Sun, Jintao Zhang, Zhaoyan Sun, Guoliang Li, Nan Tang

Proceedings of the VLDB Endowment

DOI

2021

openGauss

Guoliang Li, Xuanhe Zhou, Ji Sun, Xiang Yu, Yue Han, Lianyuan Jin, Wenbo Li, Tianqing Wang, Shifu Li

Proceedings of the VLDB Endowment

DOI

2021

DBMind

Xuanhe Zhou, Lianyuan Jin, Ji Sun, Xinyang Zhao, Xiang Yu, Jianhua Feng, Shifu Li, Tianqing Wang, Kun Li, Luyang Liu

Proceedings of the VLDB Endowment

DOI

2021

Learned Cardinality Estimation for Similarity Queries

Ji Sun, Guoliang Li, Nan Tang

Proceedings - ACM-SIGMOD International Conference on Management of Data

DOI

2021

An Autonomous Materialized View Management System with Deep Reinforcement Learning

Han Yue, Guoliang Li, Haitao Yuan, Ji Sun

Proceedings - International Conference on Data Engineering

DOI

2020

基于机器学习的数据库技术综述

李国良，周煊赫，孙佶，余翔，袁海涛，刘佳斌，韩越

《计算机学报》

2020

Database Meets Artificial Intelligence: A Survey

Xuanhe Zhou, Chengliang Chai, Guoliang Li, Ji Sun

IEEE Transactions on Knowledge and Data Engineering

DOI

2020

Query performance prediction for concurrent queries using graph embedding

Xuanhe Zhou, Ji Sun, Guoliang Li, Jianhua Feng

Proceedings of the VLDB Endowment

DOI

2020

Automatic View Generation with Deep Learning and Reinforcement Learning

Haitao Yuan, Guoliang Li, Ling Feng, Ji Sun, Yue Han

Proceedings - International Conference on Data Engineering

DOI

2020

Database Meets AI: A Survey

Xuan-He Zhou, Cheng-Liang Chai, Guo-Liang Li, Ji Sun

2019

一个端到端的基于深度学习的查询优化引擎

孙佶，李国良

《赤峰学院学报(自然科学版)》

DOI

2019

An end-to-end learning-based cost estimator

Ji Sun, Guoliang Li

Proceedings of the VLDB Endowment

DOI

2019

Balance-aware distributed string similarity-based query processing system

Ji Sun, Zeyuan Shang, Guoliang Li, Dong Deng, Zhifeng Bao

Proceedings of the VLDB Endowment

DOI

2019

Technical Report: Optimizing Human Involvement for Entity Matching and Consolidation

Ji Sun, Dong Deng, Ihab F. Ilyas, Guoliang Li, Samuel Madden, M. Ouzzani, M. Stonebraker, N. Tang

arXiv.org

2017

Dima

Ji Sun, Zeyuan Shang, Guoliang Li, Dong Deng, Zhifeng Bao

Proceedings of the VLDB Endowment

DOI

VexDB: An Agent-ready Cross-platform Multi-modal Data System

Ji Sun

AgenticData : An Agentic Data System on Heterogeneous Data

Pei-Yao Zhou, Ji Sun, Yao-Qiang Xu, Chen Qian, AgenticData

孙佶

精选作品

期刊论文

Data Agents: Agentic Data Systems

SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search

GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications

A Topology-Aware Localized Update Strategy for Graph-Based ANN Index

AgenticData: An Agentic Data Analytics System for Heterogeneous Data

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph

GaussMaster: An LLM-based Database Copilot System

GaussML: An End-to-End In-Database Machine Learning System

Database Meets Artificial Intelligence: A Survey (Extended Abstract)

人在回路的数据融合系统

AutoView: An Autonomous Materialized View Management System with Encoder-Reducer

AlphaQO: Robust Learned Query Optimizer

Learned cardinality estimation

openGauss

DBMind

Learned Cardinality Estimation for Similarity Queries

An Autonomous Materialized View Management System with Deep Reinforcement Learning

基于机器学习的数据库技术综述

Database Meets Artificial Intelligence: A Survey

Query performance prediction for concurrent queries using graph embedding

Automatic View Generation with Deep Learning and Reinforcement Learning

Database Meets AI: A Survey

一个端到端的基于深度学习的查询优化引擎

An end-to-end learning-based cost estimator

Balance-aware distributed string similarity-based query processing system

Technical Report: Optimizing Human Involvement for Entity Matching and Consolidation

Dima

VexDB: An Agent-ready Cross-platform Multi-modal Data System

AgenticData : An Agentic Data System on Heterogeneous Data

研究方向