Chunlin Tian

Ph.D Student

University of Macau

Email  |  Github  |  Twitter  |  Linkedin  |  Google Scholar

Short Bio

👋 I am a fourth-year PhD student in Computer Science at State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC), University of Macau under the supervision of Prof. Li Li and Prof. Chengzhong Xu (IEEE Fellow). Currently, I am visiting the Machine Learning Systems Group at University of Cambridge under the supervision of Prof. Nicholas D. Lane. I am also fortunate to be mentored by and to collaborate closely with Dr. Zhan Shi and Prof. Zhijiang Guo. Before joining UM, I received my BEng degree from Xi'an Jiaotong University in 2022.

💡I am broadly interested in ML for System. My current research interests focus on Efficient Machine Learning System at the Edge. On these topics, I have published 10+ papers in leading conferences/journals such as: MICRO, ATC, TPDS and SenSys (System-related); NeurIPS, ICML and IJCAI (ML-related), with several selected for Oral presentations.

Education

Selected Publications

For a complete list of my publications, please refer to my Google Scholar profile.

CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge.
Chunlin Tian, Xinpeng Qin, Kahou Tam, Li Li, Zijian Wang, Yuanzhe Zhao, Minglei Zhang and Chengzhong Xu
USENIX Annual Technical Conference (ATC), 2025
[System Conf., CCF-A, AR: 100/634 = 15.8%]
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning. [Code] [News]
Chunlin Tian, Zhan Shi, Zhijiang Guo, Li Li and Chengzhong Xu
38th Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
[ML Conf., CCF-A, Oral, AR: 61/15671 = Top 0.4%]
Ranking-based Client Imitation Selection for Efficient Federated Learning.
Chunlin Tian, Zhan Shi, Xinpeng Qin, Li Li and Chengzhong Xu
41st International Conference on Machine Learning (ICML), 2024
[ML Conf., CCF-A, AR: 2609/9653 = 27.0%]
Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting.
Chunlin Tian, Li Li, Kahou Tam, Yebo Wu, Chengzhong Xu
IEEE Transactions on Parallel and Distributed Systems (TPDS), 2024
[System Journal, CCF-A]
FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization.
Zhiyuan Ning*, Chunlin Tian*, Meng Xiao, Wei Fan, Pengyang Wang, Li Li, Pengfei Wang and Yuanchun Zhou
33rd International Joint Conference on Artificial Intelligence (IJCAI), 2024
[AI Conf., CCF-A, AR: 791/5651 = 14.0%]
FedHybrid: Breaking the Memory Wall of Federated Learning via Hybrid Tensor Management.
Kahou Tam, Chunlin Tian, Li Li, Haikai Zhao, Chengzhong Xu
22nd ACM Conference on Embedded Networked Sensor Systems (SenSys), 2024
[Mobile System Conf., CCF-B, AR: 58/313 = 18.5%]
HARMONY: Heterogeneity-Aware Hierarchical Management for Federated Learning System.
Chunlin Tian, Li Li, Zhan Shi, Jun Wang and Chengzhong Xu
55th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2022
[System Arch. Conf., CCF-A, AR: 83/369 = 22.5%]

Professional Services

Mentored Students

✨If you are passionate about research and innovation, I warmly invite you to join us on this exciting academic journey!

Awards

Teaching Assistants

    Â