Haiyun He

(Pronunciation: /ˈhaɪyuːŋ ˈhɜː/,   Pronouns: she/her/hers)
Assistant Professor, Internet of Things Thrust, HKUST(GZ)

prof_pic.jpg

(Taken at Cornell Slope)

Hi! I am currently an Assistant Professor in the Internet of Things (IoT) Thrust at the Hong Kong University of Science and Technology (Guangzhou). I am also a Cross-Campus Faculty Affiliate at HKUST. I obtained my PhD degree in Electrical and Computer Engineering from National University of Singapore in Sep. 2022, advised by Prof. Vincent Y. F. Tan. Before joining HKUST(GZ), I was a postdoc in the Center for Applied Mathematics at Cornell University, working with Prof. Ziv Goldfeld from ECE and Prof. Christina Lee Yu from ORIE. I was honored to be funded by the Center for Applied Mathematics postdoctoral fellowship.

My recent research interests lie in the intersection of information theory and machine learning, including but not limited to:

  • Machine learning and statistical learning theory
  • Hypothesis testing
  • Inference and estimation
  • Wireless communications

If you are interested in collaborating with me, please do not hesitate to drop me an email (at the bottom) or drop by my office  W3-604  !

💡 I am looking for highly motivated PhD/Mphil students and research assistants to join my group. If you are interested in exploring the intersection of information theory, machine learning, and statistics -- and have a reasonably strong background in mathematics or programming (or a strong interest in developing one) -- please feel free to reach out.

To apply, please send an email with your CV, transcript, and a brief statement of your research interests. Use the subject line: [Year]-[PhD/Mphil/RA Application]-[Your Name], e.g., 25Fall-PhD Application-Haiyun He.

News

09/30/2025 It is the academic job market season again. Some friends ask for advice on it. Here are some materials that I found useful during my search. Wish you the best luck!
09/19/2025 One paper on theoretical framework for watermarking Large Language Models (LLMs) that jointly optimizes both the watermarking scheme and the detection process is accepted by NeurIPS 2025! Congrats to my collaborators!
03/06/2025 Attending 8th C^3 Workshop at University of Florida between Mar. 06-07, 2025. My talk “Distributional Information Embedding: A Framework for LLM Watermarking” is in the afternoon on Mar. 06. Thank Sean and Yuheng for their invitation! I am glad to visit the beautiful town Gainesville, see a big family of allegators :crocodile:, and meet new friends!

Recent publications

  1. Distributional Information Embedding: A Framework for Multi-bit Watermarking
    Haiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao, and Yuheng Bu
    Asia Pacific Workshop on Data Science and Information Theory (APWDSIT), Oct 2025 (Presented at 1st Workshop on GenAI Watermarking (WMARK@ICLR))
  2. Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
    Haiyun He*, Yepeng Liu*, Ziqiao Wang, Yongyi Mao, and Yuheng Bu
    NeurIPS, Dec 2025 (Presented at 1st Workshop on GenAI Watermarking (WMARK@ICLR))
  3. Journal
    Information-Theoretic Generalization Bounds for Deep Neural Networks
    Haiyun He, and Ziv Goldfeld
    IEEE Transactions on Information Theory, May 2025