ZENG, Li
POSITION/TITLE
Principal Engineer
RESEARCH FIELD
AI Computing
zengli@sribd.cn
PERSONAL WEBSITE
https://bookug.cc/
EDUCATION BACKGROUND
Peking University, PhD of Computer science
Peking University, Bachelor of computer science
BIOGRAPHY
Dr. Li Zeng graduated with a bachelor's degree from Peking University in 2016 and earned his Ph.D. from Peking University in 2021. He has published 10+ papers, filed 5+ patents, and received numerous honors, including the GraphChallenge Innovation Award (top international graph computing competition), Huawei Awards (Talent Plan, Gold Medal Individual, Code Hero, Gold Medal Patent). He is a key contributor to renowned open-source projects such as the graph database system gStore. His primary research focuses on LLM training and inference acceleration, vector computing, graph computing, and related fields.
ACADEMIC PUBLICATIONS
1. Li Zeng (instructor). SLO-Aware Scheduling for Large Language Model Inferences. arXiv, 2025.
2. Li Zeng (instructor). WindVE: Collaborative CPU-NPU Vector Embedding. arXiv, 2025.
3. Li Zeng (second author). LocMoE: A Low-Overhead MoE for Large Language Model Training. IJCAI, 2024.
4. Li Zeng, et al. WindGP: Efficient Graph Partitioning on Heterogenous Machines. arXiv, 2024.
5. Li Zeng, et al. KBQA: Accelerate Fuzzy Path Query on Knowledge Graph. DEXA, 2023.
6. Li Zeng, Lei Zou, M. Tamer Özsu. SGSI: Scalable GPU-friendly Subgraph Isomorphism. TKDE, 2022.
7. Li Zeng, et al. HTC: Hybrid vertex-parallel and edge-parallel Triangle Counting. HPEC, 2022.
8. Li Zeng, et al. SQLG+: Efficient k-hop Query Processing on RDBMS. DASFAA, 2022.
9. Li Zeng, Lei Zou, M. Tamer Özsu, et al. GSI: GPU-friendly Subgraph Isomorphism. ICDE, 2020.
10. Li Zeng, Lei Zou. Redesign of the gStore system. FCS, 2018.
