๐จโ๐ Biography
I am Dr. Zhe Li (ๆๅฒ), currently a Postdoctoral Fellow at the The University of Hong Kong (HKU).
My research focuses on speech large language models (LLMs) ๐ง and robust speaker representation learning ๐, with a broader interest in multimodal AI for healthcare ๐ฉบ.
๐ผ Research Experience
๐ Postdoctoral Fellow, The University of Hong Kong (HKU)
Medical AI โข Speech-Language Models โข Multimodal Learning๐ป Research Intern, Microsoft Research Asia (MSRA)
Supervised by Dr. Shujie Liu
LLM fine-tuning โข Speech reasoning models โข Multilingual adaptation๐งฎ Visiting PhD Researcher, Stanford University ๐บ๐ธ
Supervised by Prof. Mert Pilanci
Optimization theory โข Efficient adaptation โข Spectral methods๐ PhD in Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University (PolyU) ๐ญ๐ฐ
Supervised by Prof. Man-Wai Mak
Speaker representation โข Speaker Verification๐ MSc in Software Engineering, Xinjiang University ๐จ๐ณ
Supervised by Prof. Wushour Silamu, Academician of the Chinese Academy of Engineering
Low-resource NLP โข Uyghur language modeling โข Harmful content detection
๐ฌ Research Interests
- ๐ Speaker Representation Learning โ disentanglement, cross-lingual robustness, and PEFT strategies
- ๐ฉบ Multimodal AI for Healthcare โ speech, text, and imaging fusion for disease prediction
- ๐ Low-Resource & Multilingual NLP โ Uyghur, morphologically rich languages, and cross-lingual transfer
You are more than what you have become!
๐ฐ News
๐ 2025
- 29 Sep 2025 โ ๐ Our paper โWhisMultiNet: Advancing End-to-End Speech Topic Classification with Whisper and MultiGateGNNโ has been accepted by IEEE Transactions on Audio, Speech, and Language Processing (T-ASLP)! Thanks to Xiaozhe Qi!
- 04 Sep 2025 โ ๐ Our paper โDisentangling Speech Representations Learning with Latent Diffusion for Speaker Verificationโ accepted by IEEE Transactions on Audio, Speech, and Language Processing (T-ASLP)! Thanks to Prof. Mak!
- 20 Aug 2025 โ ๐ One paper accepted to EMNLP 2025 โ see you in Suzhou, China!
- 18 Jun 2025 โ ๐ One paper accepted to MICCAI 2025 โ see you in Daejeon, South Korea!
- 14 Jun 2025 โ ๐ Our paper โMutual Information-Enhanced Contrastive Learning with Margin for Maximal Speaker Separabilityโ accepted by IEEE/ACM T-ASLP. Thanks to Prof. Mak!
- 19 May 2025 โ ๐ Two papers accepted to Interspeech 2025 โ see you in Rotterdam, Netherlands!
- 04 Mar 2025 โ ๐ง๐ปโ๐ซ Paper Sharing Session: I gave a talk on Spectral-Aware Low-Rank Adaptation for Speaker Verification (ICASSP 2025).
- 11 Feb 2025 โ ๐ง๐ปโ๐ป Joined Microsoft Research Asia (MSRA) as a Research Intern, focusing on multimodal large models for healthcare.
๐ 2024
- 21 Dec 2024 โ ๐ Four papers accepted to ICASSP 2025 โ see you in Hyderabad, India!
- 04 Dec 2024 โ ๐ Enhancing Multimodal Rumor Detection with Statistical Image Features and Modal Alignment via Contrastive Learning received Best Student Paper Runner-Up Award ๐ฅ at PRICAI 2024.
- 17 Jun 2024 โ ๐ง๐ปโ๐ซ Paper Sharing Session: Parameter-efficient Fine-tuning of Speaker-Aware Dynamic Prompts for Speaker Verification (Interspeech 2024).
- 03 Apr 2024 โ ๐ง๐ปโ๐ซ Paper Sharing Session: Dual Parameter-Efficient Fine-Tuning for Speaker Representation via Speaker Prompt Tuning and Adapters (ICASSP 2024).
๐ค 2023
- 08 Dec 2023 โ Presented Maximal Speaker Separability via Robust Speaker Representation Learning at NCMMSC 2023, Soochow, China.
- 03 Dec 2023 โ Presented Maximal Speaker Separability via Contrastive Learning with Angular Margin and Class-Aware Attention for Hard Samples at International Doctoral Forum 2023, Hong Kong SAR.
๐ 2022โ2020
- 15 May 2023 โ Paper Sharing Session: Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space (ICASSP 2023).
- 01 Jul 2022 โ Participant Talk: Shared on speaker verification at Odyssey-CNSRC Workshop 2022.
- 29 May 2021 โ ๐ Completed Masterโs oral examination.
- 14 Nov 2020 โ ๐ CAAI Award: Received the Excellent Scientific and Technological Achievements Award of the Chinese Association for Artificial Intelligence.
- 29 Oct 2020 โ Video: Uploaded CCL 2020 oral presentation.
- 11 Oct 2020 โ Video: Uploaded CCMT 2020 oral presentation.
