Haorui He 何昊睿

CS Ph.D. Candidate · The University of Hong Kong

EmailGoogle ScholarGitHubLinkedInX

I am a Ph.D. candidate in Computer Science at The University of Hong Kong (HKU), and a Senior Research Assistant at Hong Kong Baptist University (HKBU), supervised by Prof. Francis C.M. Lau, Prof. Reynold C.K. Cheng, and Prof. Ivan Y.P. Li. Previously, I worked under Prof. Zhizheng Wu as a Research Assistant at the Chinese University of Hong Kong (CUHK), Shenzhen and as a Research Intern at the Shanghai AI Laboratory, and as a Research Intern under Prof. Zhen Ming (Jack) Jiang at York University (YorkU). I hold a B.Eng. in Software Engineering from Nanjing University of Posts and Telecommunications (NJUPT), where I received the Outstanding Bachelor’s Thesis Award.

I am the creator of Emilia, a leading dataset for expressive and spontaneous text-to-speech (TTS) synthesis, and its preprocessing pipeline, Emilia-Pipe. Emilia has surpassed 1 million downloads from over 1k institutions and companies worldwide, including Stanford, CMU, OpenAI, Google, and NVIDIA. It is the “most liked dataset” in the audio category on HuggingFace and serves as a foundational training dataset for state-of-the-art TTS models like F5-TTS, MaskGCT, IndexTTS-2, ZipVoice, as well as Speech LLMs such as Kimi-Audio, VITA-Audio, and OmniVoice.

Research Focus

My current research interests revolve around Social Computing, where I aim to leverage LLM agents to address critical societal challenges such as misinformation & fake news.

The University of Hong Kong Hong Kong Baptist University

News

Selected Publications

† corresponding author; * equal contribution.
Google Scholar (700+ citations, h-index: 10)
  1. arXiv 2026
    Standing on the Shoulders of Giants: Enhancing LLM Agents for Automated Fact-Checking with Human Expert Skills
    Xinwen Chen, Haorui He*, and Yupeng Li.
    arXiv 2026
    Paper
  2. MM 2026
    Novel Claim or Déjà Vu? Rethinking "Contamination-Free" Dynamic Evaluation for Multimodal Automated Fact-Checking
    Haorui He, Xinwen Chen, Dacheng Wen, Reynold Cheng, Francis C. M. Lau, and Yupeng Li.
    MM 2026 (Acceptance rate: 26.4%)
    GitHub / Paper / Website / Tweet / Chinese Blog
  3. WWW 2026
    Debating Truth: Debate-Driven Claim Verification with Multiple Large Language Model Agents
    Haorui He, Yupeng Li, Dacheng Wen, Yang Chen, Reynold Cheng, Donglong Chen, and Francis C. M. Lau.
    WWW 2026 (Web4good Special Track; Acceptance rate: 21.7%)
    GitHub / Paper
  4. AAAI 2026
    Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-Checking System
    Haorui He, Yupeng Li, Bin Benjamin Zhu, Dacheng Wen, Reynold Cheng, and Francis C. M. Lau.
    AAAI 2026 (Oral; Acceptance rate: 4.7%; 100K views on Weibo)
    GitHub / Paper / Website / Chinese Blog
  5. APSIPA 2025
    Noro: Noise-Robust One-Shot Voice Conversion with Hidden Speaker Representation Learning
    Haorui He, Yuchen Song, Yuancheng Wang, Haoyang Li, Xueyao Zhang, Li Wang, Gongping Huang, Eng Siong Chng, and Zhizheng Wu.
    APSIPA 2025 (Best Paper Finalist, Acceptance rate: 1.4%)
    Paper / Chinese Blog
  6. TASLP 2025
    Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation
    Haorui He, Zengqiang Shang, Chaoren Wang, Xuyuan Li, Yicheng Gu, Hua Hua, Liwei Liu, Chen Yang, Jiaqi Li, Peiyang Shi, Yuancheng Wang, Kai Chen, Pengyuan Zhang, and Zhizheng Wu.
    IEEE Transactions on Audio, Speech and Language Processing (TASLP) 2025 (Ranked #1 most-liked/trending audio dataset on HuggingFace with over 1 million downloads)
    GitHub GitHub stars / Paper / HuggingFace / Demo / Tweet
  7. Technical Report 2025
    Overview of the Amphion Toolkit (v0.2)
    Jiaqi Li, Xueyao Zhang, Yuancheng Wang, Haorui He*, Chaoren Wang, Li Wang, Huan Liao, Junyi Ao, Zeyu Xie, Yiqiao Huang, Junan Zhang, and Zhizheng Wu.
    Technical Report 2025 (Ranked #1 trending on GitHub with 10k+ stars)
    GitHub GitHub stars / Paper / HuggingFace / Tweet
  8. WWW 2024
    MCFEND: A Multi-Source Benchmark Dataset for Chinese Fake News Detection
    Yupeng Li, Haorui He†, Jin Bai, and Dacheng Wen.
    WWW 2024 (Oral Presentation, Acceptance rate: 9.4%)
    GitHub / Paper / Website
  9. TCSS 2023
    Improved Target-Specific Stance Detection on Social Media Platforms by Delving into Conversation Threads
    Yupeng Li, Haorui He†, Shaonan Wang, Francis C.M. Lau, and Yunya Song.
    IEEE Transactions on Computational Social Systems (TCSS) 2023 (The first paper in conversational stance detection)
    GitHub / Paper

Education

The University of Hong Kong (HKU)

Ph.D. Candidate, School of Computing and Data Science

Supervisors: Prof. Francis C.M. Lau, Prof. Reynold C.K. Cheng, Prof. Ivan Y. P. Li (HKBU)

Sep 2024 -- Present

Nanjing University of Posts and Telecommunications (NJUPT)

B.Eng. in Software Engineering (GPA: 90.07/100)

Aug 2019 -- Jun 2023

Experience

Hong Kong Baptist University

Senior Research Assistant @ Hong Kong

Trustworthy LLM Agents for Fact-Checking, Supervisor: Prof. Ivan Y. P. Li

Nov 2024 -- Present

Shanghai AI Laboratory

Research Intern @ Shanghai

Speech LLM, Zero-Shot Text-to-Speech Synthesis, Supervisor: Prof. Zhizheng Wu

Feb 2024 -- Oct 2024

Chinese University of Hong Kong, Shenzhen

Research Assistant @ Shenzhen

Speech Deepfake Detection, Voice Conversion, Supervisor: Prof. Zhizheng Wu

Sep 2023 -- Feb 2024

York University

Research Intern @ Toronto

Active Machine Learning, Code Intelligence, Supervisor: Prof. Zhen Ming (Jack) Jiang

Sep 2022 -- Dec 2022

The University of Hong Kong

Research Intern @ Hong Kong

Stance Detection, Fake News Detection, Supervisors: Prof. Francis C.M. Lau, Prof. Ivan Y. P. Li

May 2021 -- Aug 2023

Awards

Services

Misc

"Facts do not cease to exist because they are ignored." -- Aldous Huxley

Last updated: Oct 2026