Profile-Photo-Zimu 

Zimu Zhou | 周子慕

Assistant Professor
Department of Data Science
City University of Hong Kong

16-226, 16/F, Lau Ming Wai Academic Building,
City University of Hong Kong,
83 Tat Chee Avenue, Kowloon Tong, Hong Kong
zimuzhou [at] cityu [dot] edu [dot] hk

News

Biography

Zimu Zhou is currently an assistant professor at the Department of Data Science, City University of Hong Kong. He received his Ph.D. in 2016 in the Department of Computer Science and Engineering, Hong Kong University of Science and Technology (HKUST), under supervision of Prof. Linoel M. Ni and Prof. Yunhao Liu. He received his B.E. in 2011 in the Department of Electronic Engineering, Tsinghua University. From 2016 to 2019, he was a postdoctoral researcher at the Computer Engineering and Networks Laboratory, ETH Zurich, under supervision of Prof. Dr. Lothar Thiele. From 2020 to 2022, he was an assistant professor at the School of Computing and Information Systems, Singapore Management University (SMU).

Research Interests

My research broadly lies in mobile and ubiquitous computing, with current interests in on-device AI, collaborative AI, and data management for AI. I am particularly interested in enabling efficient and adaptive AI applications on resource-constrained devices and across distributed environments. My earlier work focused on IoT sensing and applications.

Recent Publications

[Full List] [Google Scholar] [DBLP]
* Corresponding Author

On-device AI

  1. [UbiComp’26] Wentao Zhou, Sicong Liu, Zimu Zhou, Yimeng Duan, Yongyan Cai, Weiye Wu, Teng Li, Daqing Zhang, and Zhiwen Yu, ‘‘UIAnchor: Anchoring UI Perception and Action Execution for Reliable Service-Composed Mobile Task Automation with GUI Agents’’, In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol.10, no.3, pp.197:1-197:27, 2026, Shanghai, China, Oct 11 - Oct 15, 2026. [pdf]

  2. [CVPR’26] Cheng Fang, Zimu Zhou*, Ke Ma, Bin Guo, ‘‘TaskIT: Memory-Efficient Fine-Tuning of Multi-LoRA LLMs via Cross-Task Importance Transfer’’, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Denver, USA, Jun 03 - Jun 07, 2026. [pdf]

  3. [SenSys’24] Cheng Fang, Sicong Liu, Zimu Zhou, Bin Guo, Jiaqi Tang, Ke Ma, Zhiwen Yu, ‘‘AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environments’’, In Proceedings of the ACM Conference on Embedded Networked Sensor Systems, Hangzhou, China, Nov 04 - Nov 07, 2024. (AR: 58/313 = 18.5%) [pdf] (Best Paper Honorable Mentions)

  4. [MobiSys’24] Lixiang Han, Zimu Zhou*, Zhenjiang Li*, ‘‘Pantheon: Preemptible Multi-DNN Inference on Mobile Edge GPUs’’, In Proceedings of the ACM International Conference on Mobile Systems, Applications, and Services, Tokyo, Japan, Jun 03 - Jun 07, 2024. (AR: 43/263 = 16.3%) [pdf]

  5. [UbiComp’23] Yanfei Wang, Zhiwen Yu, Sicong Liu, Zimu Zhou, Bin Guo, ‘‘Genie in the Model: Automatic Generation of Human-in-the-Loop Deep Neural Networks for Mobile Applications’’, In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol.7, no.1, pp.36:1-36:29, 2023, Cancun, Mexico, Oct 08 - Oct 12, 2023. [pdf]

  6. [KDD’22] Zhongnan Qu, Zimu Zhou*, Yongxin Tong, Lothar Thiele, ‘‘p-Meta: Towards On-device Deep Model Adaptation’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, Aug 14 - Aug 18, 2022. (Research Track) (AR: 254/1695 = 15.0%) [pdf]

  7. [KDD’22] Dawei Gao, Yuexiang Xie, Zimu Zhou, Zhen Wang, Yaliang Li, Bolin Ding, ‘‘Finding Meta Winning Ticket to Train Your MAML’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, Aug 14 - Aug 18, 2022. (Research Track) (AR: 254/1695 = 15.0%) [pdf]

  8. [KDD’21] Xiaoxi He, Dawei Gao, Zimu Zhou*, Yongxin Tong, Lothar Thiele, ‘‘Pruning-Aware Merging for Efficient Multitask Inference’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Virtual, Aug 14 - Aug 18, 2021. (Research Track) (AR: 238/1541 = 15.4%) [pdf]

  9. [KDD’20] Dawei Gao, Xiaoxi He, Zimu Zhou*, Yongxin Tong, Ke Xu, Lothar Thiele, ‘‘Rethinking Pruning for Accelerating Deep Inference at the Edge’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Virtual, Aug 23 - Aug 27, 2020. (Research Track) (AR: 216/1279 = 16.9%) [pdf] [code]

  10. [CVPR’20] Zhongnan Qu, Zimu Zhou*, Yun Cheng, Lothar Thiele, ‘‘Adaptive Loss-aware Quantization for Multi-bit Networks’’, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual, Jun 14 - Jun 19, 2020. (AR: 1470/6656 = 22.1%) [pdf] [supplementary] [code]

Collaborative AI

  1. [INFOCOM’26] Boyi Liu, Zimu Zhou*, Pengfei Gao, Shuo Kang, Yongxin Tong*, ‘‘Towards Asynchronous Client Collaboration in Personalized Federated Learning’’, In Proceedings of the IEEE International Conference on Computer Communications, Tokyo, Japan, May 18 - May 21, 2026. (AR: 329/1740 = 18.9%) [pdf]

  2. [KDD’25] Lehao Qu, Shuyuan Li, Zimu Zhou, Boyi Liu, Yi Xu, Yongxin Tong, ‘‘DarkDistill: Difficulty-Aligned Federated Early-Exit Network Training on Heterogeneous Devices’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Toronto, Canada, Aug 03 - Aug 07, 2025. (Research Track) [pdf]

  3. [ICDE’25] Shuyue Wei, Yongxin Tong, Zimu Zhou, Tianran He, Yi Xu, ‘‘Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approach’’, In Proceedings of the IEEE International Conference on Data Engineering, Hong Kong, China, May 19 - May 23, 2025. (Research Track)

  4. [MobiCom’24] Kun Wang, Zimu Zhou*, Zhenjiang Li*, ‘‘LATTE: Layer Algorithm-aware Training Time Estimation for Heterogeneous Federated Learning’’, In Proceedings of the ACM Annual International Conference on Mobile Computing and Networking, Washington, D.C., USA, Nov 18 - Nov 22, 2024. [pdf]

  5. [UbiComp’24] Xiaochen Li, Sicong Liu, Zimu Zhou, Bin Guo, Yuan Xu, Zhiwen Yu, ‘‘EchoPFL: Asynchronous Personalized Federated Learning on Mobile Devices with On-Demand Staleness Control’’, In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol.8, no.1, pp.41:1-41:22, 2024, Melbourne, Australia, Oct 05 - Oct 09, 2024. [pdf]

  6. [KDD’24] Boyi Liu, Yiming Ma, Zimu Zhou, Yexuan Shi, Shuyuan Li, Yongxin Tong, ‘‘CASA: Clustered Federated Learning with Asynchronous Clients’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, Aug 25 - Aug 29, 2024. (Research Track) (AR: 409/2046 = 20.0%) [pdf]

  7. [KDD’24] Linghua Yang, Wantong Chen, Xiaoxi He, Shuyue Wei, Yi Xu, Zimu Zhou, Yongxin Tong, ‘‘FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, Aug 25 - Aug 29, 2024. (Applied Data Science Track) (AR: 147/738 = 20.0%) [pdf]

  8. [KDD’23] Wenhao Zhang, Zimu Zhou, Yansheng Wang, Yongxin Tong, ‘‘DM-PFL: Hitchhiking Generic Federated Learning for Efficient Shift-Robust Personalization’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Long Beach, CA, USA, Aug 06 - Aug 10, 2023. (Research Track) (AR: 313/1416 = 22.1%) [pdf]

  9. [ICDE’23] Yansheng Wang, Yongxin Tong, Zimu Zhou, Ruisheng Zhang, Sinno Jialin Pan, Lixin Fan, Qiang Yang, ‘‘Distribution-Regularized Federated Learning on Non-IID Data’’, In Proceedings of the IEEE International Conference on Data Engineering, Anaheim, CA, USA, Apr 03 - Apr 07, 2023. (Research Track) [pdf]

  10. [KDD’22] Yansheng Wang, Yongxin Tong, Zimu Zhou, Ziyao Ren, Yi Xu, Guobin Wu, Weifeng Lv, ‘‘Fed-LTD: Towards Cross-Platform Ride Hailing via Federated Learning to Dispatch’’, In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, Aug 14 - Aug 18, 2022. (Applied Data Science Track) [pdf]

Data Management for AI

  1. [SIGIR’26] Zhilin Liang, Yuxiang Wang, Zimu Zhou, Hainan Zhang, Boyi Liu, Yongxin Tong, ‘‘FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters’’, In Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, Melbourne, Australia, Jul 20 - Jul 24, 2026. [pdf] (AR: 234/1271 = 18.4%)

  2. [ICDE’26] Yuxiang Wang, Yongxin Tong, Zimu Zhou, Ziyuan He, Ruixi Hu, Ke Xu, ‘‘Federated Retrieval over Embedding-Heterogeneous Vector Databases’’, In Proceedings of the IEEE International Conference on Data Engineering, Montreal, Canada, May 04 - May 08, 2026. (Research Track) [pdf]

  3. [ICDE’25] Yuxiang Wang, Ziyuan He, Yongxin Tong, Zimu Zhou, Yiman Zhong, ‘‘Timestamp Approximate Nearest Neighbor Search over High-Dimensional Vector Data’’, In Proceedings of the IEEE International Conference on Data Engineering, Hong Kong, China, May 19 - May 23, 2025. (Research Track) [pdf]

Professional Activities

Honors & Awards

Group

Teaching