Boyi Liu | 刘博一 Ph.D. Student † School of Computer Science and Engineering, Beihang University ‡ Department of Data Science, City University of Hong Kong [GitHub] [DBLP] [Google Scholar] Email: boyliu [at] buaa [dot] edu [dot] cn

Biography

Boyi Liu is a Ph.D. student at the Beihang University, supervised by Prof. Yongxin Tong. He is also a joint Ph.D. student at the City University of Hong Kong, supervised by Prof. Zimu Zhou. His research focuses on Efficient and Personalized Edge AI. He has been working on cross-device federated learning. Recently, his research interests include:

• On-device Data Curation for LLM Finetuning

• On-device Agent Memory Systems

News

• [2026/06] One technique report for LLM data selection is available now.

• [2026/04] One paper for federated retrieval-augmented generation was accepted by SIGIR 2026.

• [2026/02] Two papers for early-exit network training and federated retrieval-augmented generation are preprint on arXiv now.

• [2026/01] One paper for multimodal federated learning was accepted by DASFAA 2026.

• [2025/12] One paper for personalized federated learning was accepted by INFOCOM 2026.

• [2025/08] One poster paper for asynchronous federated learning was accepted by MobiCom 2025.

Publications

2026

1. A Review on Data Selection for LLM Finetuning
   Boyi Liu
   Technique Report, 2026
   [Paper]
2. CAFEDistill: Learning Personalized and Dynamic Models through Federated Early-Exit Network Distillation
   Boyi Liu, Zimu Zhou, Cheng Fang, Yongxin Tong
   Preprint, 2026
   [Paper] [Code]
3. FedLLM-Factory: A Unified Framework for Federated Large Language Model Fine-tuning
   Boyi Liu
   Technique Report, 2026
   [Paper] [Code]
4. Towards Asynchronous Client Collaboration in Personalized Federated Learning
   Boyi Liu, Zimu Zhou, Pengfei Gao, Shuo Kang, Yongxin Tong
   IEEE International Conference on Computer Communications (INFOCOM), 2026
   [Paper] [Code]
5. Harnessing Asynchrony to Balance Modalities in Multi-Modal Federated Learning
   Yiming Ma, Boyi Liu, Zimu Zhou, Yanfeng Wang, Yongxin Tong
   International Conference on Database Systems for Advanced Applications (DASFAA), 2026
   [Paper]
6. FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters
   Zhilin Liang, Yuxiang Wang, Zimu Zhou, Hainan Zhang, Boyi Liu, Yongxin Tong
   International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2026
   [Paper] [Code]

2025

7. Poster: Asynchronous Federated Learning Library and Benchmark with AFL-Lib
   Boyi Liu, Shuyuan Li, Zimu Zhou, Shuo Kang, Yiming Ma, Yongxin Tong
   ACM Annual International Conference on Mobile Computing and Networking (MobiCom), 2025
   [Paper] [Code] [Poster]
8. FedAIMS: Personalized Federated Learning with Adaptive Intermediate Supervision
   Shuyuan Li, Boyi Liu, Zimu Zhou, Jin Dong
   Frontiers of Computer Science (FCS), 2025
   [Paper] [Code]
9. DarkDistill: Difficulty-Aligned Federated Early-Exit Network Training on Heterogeneous Devices
   Lehao Qu, Shuyuan Li, Zimu Zhou, Boyi Liu, Yi Xu, Yongxin Tong
   ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025
   [Paper] [Slides] [Poster]
10. Factor for Agent (FAgent): Collaborative Learning of Large and Small Language Models
    Shuyuan Li, Yongxin Tong, Qiang Yang, Zimu Zhou, Boyi Liu
    Computing Magazine of the CCF (CCCF), 2025
    [Paper]

2024 and Before

11. CASA: Clustered Federated Learning with Asynchronous Clients
    Boyi Liu, Yiming Ma, Zimu Zhou, Yexuan Shi, Shuyuan Li, Yongxin Tong
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2024
    [Paper] [Slides] [Poster]
12. Federated Computing: Query, Learning, and Beyond
    Yongxin Tong, Yuxiang Zeng, Zimu Zhou, Boyi Liu, Yexuan Shi, Shuyuan Li, Ke Xu, Weifeng Lv
    IEEE Data Engineering Bulletin (DEB), 2023
    [Paper]
13. Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand Prediction
    Ruixing Zhang, Liangzhe Han, Boyi Liu, Jiayuan Zeng, Leilei Sun
    International Joint Conference on Artificial Intelligence (IJCAI), 2022
    [Paper] [Code]

Educations

• Joint Ph.D. Department of Data Science, City University of Hong Kong, 2024 - 2028 (Expected)

• Ph.D. School of Computer Science and Engineering, Beihang University, 2023 - 2028 (Expected)

• B.E. School of Computer Science and Engineering, Beihang University, 2019 - 2023