Baotong Lu Researcher Systems and Networking Research Group Microsoft Research Asia (MSR Asia) Email: baotonglu[@]microsoft.com Github: baotonglu

Biography

Baotong Lu is a researcher in Microsoft Research Asia. He received his PhD degree from The Chinese University of Hong Kong in 2023 and visited Simon Fraser University in 2019 and 2023 respectively. His research interest lies in database management system (e.g., vector databases) and machine learning systems (e.g., LLM inference, RAGs). He is a recipient of 2021 ACM SIGMOD Research Highlight Award. Two of his papers (Dash and APEX) are selected as Most Influential ArXiv (Databases) Papers (Top-30 per year).

I am actively looking for interns who are passionate about system research. Being familiar with GPU programming is a plus.

Publications

*Students I advised

• RetroInfer: A Vector-Storage Approach for Scalable Long-Context LLM Inference
  Yaoqi Chen*, Jinkai Zhang*, Baotong Lu⁺, Qianxi Zhang, Chengruidong Zhang, Jingjia Luo*, Di Liu, Huiqiang Jiang, Qi Chen, Jing Liu, Bailu Ding, Xiao Yan, Jiawei Jiang, Chen Chen, Mingxing Zhang, Yuqing Yang, Fan Yang, Mao Yang
  (⁺ Corresponding author)
  Preprint
  

• Missile: Fine-Grained, Hardware-Level GPU Resource Isolation for Multi-Tenant DNN Inference
  Yongkang Zhang, Haoxuan Yu, Chenxia Han, Cheng Wang, Baotong Lu, Yang Li, Xiaowen Chu, Huaicheng Li
  PPoPP 2025

• RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
  Di Liu*, Meng Chen*, Baotong Lu, Huiqiang Jiang, Zhenhua Han, Qianxi Zhang, Qi Chen, Chengruidong Zhang, Bailu Ding, Kai Zhang, Chen Chen, Fan Yang, Yuqing Yang, LiLi Qiu
  NeurIPS 2024 ENLSP workshop (Oral)
  Best Paper Award
  

• DEX: Scalable Range Indexing on Disaggregated Memory
  Baotong Lu, Kaisong Huang, Mike Chieh-Jan Liang, Tianzheng Wang, Eric Lo
  50th International Conference on Very Large Data Bases (VLDB 2024).

• Are Updatable Learned Indexes Ready?
  Chaichon Wongkham, Baotong Lu, Chris Liu, Zhicong Zhong, Eric Lo, Tianzheng Wang
  48th International Conference on Very Large Data Bases (VLDB 2022).

• APEX: A High-Performance Learned Index on Persistent Memory.
  Baotong Lu, Jialin Ding, Eric Lo, Umar Faroop Minhas, Tianzheng Wang
  48th International Conference on Very Large Data Bases (VLDB 2022).

• Scaling Dynamic Hash Tables on Real Persistent Memory. [Technical Perspective] from Prof. Ken Ross
  Baotong Lu, Xiangpeng Hao, Tianzheng Wang, Eric Lo
  SIGMOD Record 2021, Volume 50, Issue 1.

• Dash: Scalable Hashing on Perisistent Memory. [code] [Abstract at NVMW 2021]
  Baotong Lu, Xiangpeng Hao, Tianzheng Wang, Eric Lo
  46th International Conference on Very Large Data Bases (VLDB 2020).
  2021 ACM SIGMOD Research Highlight Award
  DragonflyDB's (a modern, fast Redis replacement) core hash table structure is based on Dash.

• High Performance Depthwise and Pointwise Convolutions on Mobile Devices.
  Pengfei Zhang, Eric Lo, Baotong Lu
  34th AAAI conference on Artificial Intelligence (AAAI 2020).

Professional Service

• VLDB Journal Reviewer Board Member, 2025--2026

• Program Committee: ICDE 2026

• Program Committee: EDBT 2026

• Program Committee: VLDB 2025 (PVLDB 18)

• Program Committee: APSys 2025

• Program Committee: ChinaSys 2025, 2024

• SIGMOD Availability Committee 2023, 2022

• Reviewer: VLDBJ, ACM TOS, IEEE TKDE, IEEE TCAD

• External Reviewer: SIGMOD 2024, ICDE 2024, SIGMOD 2022, ICDE 2022, VLDB 2021, SIGMOD 2021, ICDE 2021, EDBT 2021, ATC 2020, DASFAA 2019, VLDB 2018 (Demo)

Teaching Assistant (CUHK)

• Spring 2021, CSCI5570: Large Scale Data Processing Systems

• Fall 2020, CENG4480: Embedded System Development and Applications

• Fall 2019, CSCI4160: Distributed and Parallel Computing

• Spring 2019, ESTR3102: Operating Systems (Elite Stream)

• Fall 2018, CSCI3150: Operating Systems

Selected Awards

Best Paper Award, ENLSP Workshop @ NeurIPS	2024
ACM SIGMOD Research Highlight Award	2021
Mitacs Globalink Research Award	2022
China National Scholarship	2015, 2017