Xiaomin Ouyang

Xiaomin_OUYANG_photo.jpeg
Assistant Professor

Department of Computer Science and Engineering

Hong Kong University of Science and Technology

Email:xmouyang@cse.ust.hk

Office:Room 3562, Academic Building, HKUST, Clear Water Bay, Kowloon, Hong Kong

I am an Assistant Professor at Department of Computer Science & Engineering, Hong Kong University of Science and Technology (HKUST) since Fall 2024. I lead the HKUST Mobile, Intelligent, and Networked System (MINSys) Group. Previously, I was a postdoctoral researcher at UCLA Networked & Embedded Systems Lab, working with Prof. Mani Srivastava. I obtained my Ph.D. degree from The Chinese University of Hong Kong in 2023, advised by Prof. Guoliang Xing, and co-advised by Prof. Jianwei Huang. I received ACM MobiSys Best Paper Award and ACM SIGBED China Outstanding Doctoral Dissertation Award. I was named one of EECS Rising Stars in 2023 and mHealth Scholars in 2024.

My current research interest is empowering mobile and IoT devices with AI to create ambient intelligence for smart health applications.

  • Machine Learning for IoT Systems: address real-world data and system challenges for advancing ML in mobile/IoT systems.
  • Smart Health: design and deploy real-world IoT systems for personalized health monitoring and intervention, e.g., monitoring digital biomarkers of Alzheimer’s Disease.
  • Mobile Sensing: enhance sensing quality with physics-strengthened AI techniques, e.g., exposing high-resolution texture information from ToF cameras.

I am always actively looking for highly motivated students to join my group (Earliest round for Ph.D.: 2025 Spring/Fall). I also have several research internship positions opening starting anytime. See openings for more details. Please email me your CV and transcript if you are interested in.

Recent News

Nov 2024 Invited to serve as TPC for ACM SenSys 2025, please consider submitting!
Oct 2024 Invited to serve as TPC for ACM MobiSys 2025, please consider submitting!
Sep 2024 One paper on foundation model for building analytics accepted by BuildSys’24.
Aug 2024 Started as a tenure-track assistant professor @ HKUST CSE.
Jul 2024 FlexLoc accepted by IROS 2024.
Jun 2024 Invited to serve as TPC for ACM SenSys 2024, please consider submitting!

Selected Publications

2024

  1. BuildSys’24
    Are Time Series Foundation Models Ready to Revolutionize Predictive Building Analytics?
    Ozan Baris Mulayim, Pengrui Quan, Liying Han, and 4 more authors
    In Proceedings of the 11th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, 2024
    PDF Code Slides
  2. MobiCom’24
    ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer’s Disease
    Xiaomin Ouyang, Xian Shuai, Yang Li, and 12 more authors
    In Proceedings of the 30th Annual International Conference on Mobile Computing and Networking, May 2024
    PDF Code
  3. SenSys-ML’24
    LLMSense: Harnessing LLMs for High-level Reasoning Over Spatiotemporal Sensor Traces
    Xiaomin Ouyang, and Mani Srivastava
    Mar 2024
    PDF

2023

  1. MobiSys’23
    Harmony: Heterogeneous Multi-Modal Federated Learning through Disentangled Model Training
    Xiaomin Ouyang, Zhiyuan Xie, Heming Fu, and 6 more authors
    In Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services, Jun 2023
    PDF Code Slides
  2. MobiSys’23
    Mozart: A Mobile ToF System for Sensing in the Dark through Phase Manipulation
    Zhiyuan Xie(co-primary), Xiaomin Ouyang(co-primary), Li Pan, and 3 more authors
    In Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services, Jun 2023
    Best Paper Award
    PDF Code Slides

2022

  1. MobiCom’22
    Cosmo: Contrastive Fusion Learning with Small Data for Multimodal Human Activity Recognition
    Xiaomin Ouyang, Xian Shuai, Jiayu Zhou, and 4 more authors
    In Proceedings of the 28th Annual International Conference on Mobile Computing And Networking, Oct 2022
    PDF Code Slides

2021

  1. MobiSys’21
    ClusterFL: A Similarity-Aware Federated Learning System for Human Activity Recognition
    Xiaomin Ouyang, Zhiyuan Xie, Jiayu Zhou, and 2 more authors
    In Proceedings of the 19th Annual International Conference on Mobile Systems, Applications, and Services, Jun 2021
    PDF Video Code Slides Dataset