👤 Biography

Zhe Li is a Postdoctoral Fellow at The University of Hong Kong. His research interests include speech LLMs, robust speaker representation learning, and multimodal artificial intelligence for healthcare applications. He received his Ph.D. in Electrical and Electronic Engineering from The Hong Kong Polytechnic University in 2025, his M.Sc. in Software Engineering from Xinjiang University in 2021, and his B.Eng. in Computer Science from Qilu University of Technology in 2016. He was a research intern at Microsoft Research Asia (MSRA) in 2025 and a visiting Ph.D. researcher in the Department of Electrical Engineering at Stanford University in 2024. He has led two research projects and contributed to a project funded by the Hong Kong Research Grants Council. He has published more than 60 papers in leading speech journals and conferences, including IEEE TASLP, ICASSP, and INTERSPEECH. He holds three granted invention patents and one software copyright. He delivered tutorials on speech large language models at ICME 2026 and INTERSPEECH 2026, and co-organized a special session at ACM MMAsia 2026. He received the 2020 Outstanding Scientific and Technological Achievement Award from the Chinese Association for Artificial Intelligence. His co-authored work received the Best Student Paper Runner-Up Award at PRICAI 2024.

“You are more than what you have become!”

📢 News

• Sep. 9, 2026: 🎉 Our paper “ML-CIF: Multi-Layer Continuous Integrate-and-Fire for Text-Dependent Speaker Verification” has been accepted for poster presentation at IEEE SLT 2026. Congratulations to Ruichen Zuo and all co-authors — see you in Palermo, Italy! 🇮🇹
• Dec. 2026: Organizing the Special Session on Trustworthy Speech and Audio AI at MMAsia 2026.
• Sept. 27, 2026: Presenting the Speech Large Language Models for Under-Resourced Languages tutorial at Interspeech 2026 in Sydney, Australia.
• Sept. 4, 2026: Gave an invited talk, What to Learn and Where to Adapt: Efficient Post-Training of Speech Foundation Models, at the DNAs Seminar Series, Duke Kunshan University.
• Jul. 9, 2026: Presented the Speech Large Language Models: Architectures, Efficient Adaptation, and Applications tutorial at IEEE ICME 2026 in Bangkok, Thailand.
• Jul. 2026: 🎉 Our paper “Towards Robust Remote Sensing Visual Question Answering with Spectral Expert Adaptation and Group-Relative Optimization” has been accepted for publication in Neural Networks.
• Jul. 2026: 🎉 Our paper “STEP: Semantic-Guided Two-Stage Framework with Skeleton-Conditioned Prompting for Skeleton-Based Action Recognition” has been accepted to PRCV 2026. Kudos to Zheng Cui for leading this work!

🎙️ Research Interests

• Speech large language models: multilingual modeling, parameter-efficient fine-tuning, and post-training alignment
• Speech processing: speaker representation learning, speaker verification, and robust speech modeling
• AI for health: speech-related health applications and multimodal representation learning

💼 Academic Positions

• Postdoctoral Fellow, The University of Hong Kong, Hong Kong SAR — Nov. 2025–Present
• Research Scientist (Intern), Microsoft Research Asia, Beijing, China — Feb. 2025–Oct. 2025
• Visiting PhD Researcher, Stanford University, California, USA — Mar. 2024–Nov. 2024

🎓 Education

• PhD in Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong SAR — Jan. 2022–Oct. 2025
• Master in Software Engineering, Xinjiang University, Xinjiang, China — Sept. 2018–June 2021
• Undergraduate in Computer Science, Qilu University of Technology, Shandong, China — Sept. 2012–June 2016

🏆 Selected Awards

• Best Student Paper Runner-Up Award, Pacific Rim International Conference on Artificial Intelligence (PRICAI 2024), November 2024
• Outstanding Scientific and Technological Achievement Award, Chinese Association for Artificial Intelligence (CAAI), October 2020
• Top 100 Teams Award, Intel Cup’s Inaugural Chinese Graduate Student Artificial Intelligence Innovation Competition, June 2019