Hello and welcome!

I am a tenure-track Assistant Professor in the Data Science and Analytics (DSA) Thrust at the Information Hub, The Hong Kong University of Science and Technology (Guangzhou), where I lead the Sustainable Computing (SusCom) Lab. Our research leverages machine learning and data science techniques to address computational sustainability challenges, with a special focus on AI infrastructure. Our current research interests include:

  • Energy-efficient AI model serving, particularly focusing on large language models (LLMs);
  • Computational resource management, including scheduling, dispatching, and orchestrating, in cloud and edge environments.

We are also interested in developing AI-aided and practical solutions for power monitoring, modeling, and saving in smart homes & buildings. Typical research problems we are tackling include:

  • Non-intrusive load monitoring (NILM) for smart homes;
  • Integrating LLM agents into building energy systems (BESs).
Recruitment: I am actively seeking self-motivated PhD students, RAs, and Interns to join my research group. If you are interested, please send your CV and transcripts to my email below.

Email: guomingtang [at] hkust-gz [dot] edu [dot] cn

News

  • Apr. 2025: ZSMerge (zero-shot KV Cache Compression for LLMs) is now available on arXiv and open-sourced on GitHub.
  • Mar. 2025: GreenFL and SAGkit got accepted to ICDCS’25 and ICDCSW’25, respectively.
  • Mar. 2025: Three papers got accepted to IEEE TIFS, TGCN and TVT, respectively.
  • Nov. 2024: Our paper on real-world NILM system deployment won the Best Paper Award of SustainCom’24.
  • Jun. 2024: Our work on low-carbon edge computing system got accepted to ICPP’24.
  • Mar. 2024: One paper got accepted to IEEE TPDS.
  • Jan. 2024: Two papers got accepted to IEEE Network and TMC, respectively.
  • Dec. 2023: One Paper got accepted to IEEE TPDS.
  • Nov. 2023: Two papers got accepted to IEEE TGCN and IoT-J, respectively.
  • Aug. 2023: One survey paper got accpeted to ACM Computing Surveys.
  • Aug. 2023: Three papers got accepted to IEEE IoT-J.
  • May. 2023: One paper got accepted to ICDCS’23.
  • May. 2023: FedNILM was published by IEEE TGCN.
  • Apr. 2023: HyEdge got accepted to ACM TIOT.