PeopleofSuperintelligence

Researcher

Lequan Yu

Lequan Yu is an AI researcher who develops machine learning methods for medical-image analysis and healthcare. After earning a computer science degree at Zhejiang University and a CSE PhD at CUHK, he held research internships at Siemens and NVIDIA and a postdoctoral fellowship at Stanford. His research includes uncertainty-aware segmentation of 3D left-atrium MR images and FLEX, a knowledge-guided method for adapting pathology foundation models; he was runner-up for the MICCAI Young Scientist Publication Impact Award in 2023 and 2024. As of October 2026, he is an assistant professor at the University of Hong Kong and directs its Medical AI Lab.

Now at
School of Computing and Data Science
Badges

Timeline

  1. 2015

    A Zhejiang computer science degree

    He earns a B.Eng. in computer science at Zhejiang University in 2015.

  2. 2017–2018

    Medical imaging internships

    At Siemens Healthineers in 2017, he researches body-landmark detection with deep reinforcement learning. At NVIDIA in 2018, he works on few-shot medical image segmentation.

  3. 2019

    A PhD at CUHK

    He completes a PhD in computer science and engineering at The Chinese University of Hong Kong in 2019.

  4. 2019

    Semi-supervised left-atrium segmentation

    At MICCAI 2019, he coauthors a paper introducing an uncertainty-aware teacher-student framework for semi-supervised left-atrium segmentation from 3D MR images.

  5. November 2019–March 2021

    Postdoctoral research at Stanford

    From November 2019 to March 2021, he is a postdoctoral research fellow at Stanford University, advised by Lei Xing.

  6. 2023–2024

    MICCAI award runner-up

    In 2023 and 2024, he is runner-up for the MICCAI Young Scientist Publication Impact Award.

  7. 2025

    Pathology foundation model adaptation

    In 2025, he coauthors FLEX, a framework that uses visual and textual domain knowledge to adapt pathology foundation models and improve cross-domain generalization and demographic fairness.

  8. As of October 2026

    Assistant professor and lab director

    As of October 2026, he is an assistant professor in the Division of AI & Data Science at HKU's School of Computing and Data Science and directs the Medical AI Lab. His research spans medical image analysis, machine learning, computer vision, clinical NLP and AI in healthcare.

Career

  1. NowSchool of Computing and Data ScienceAssistant Professor
  2. NowUniversity of Hong KongDirector
  3. 2019–2021Stanford UniversityPostdoctoral Research Fellow
  4. 2018NVIDIAResearch Intern
  5. 2017Siemens HealthineersResearch Intern

Education

  1. 2019Chinese University of Hong KongPhD in computer science and engineering
  2. 2015Zhejiang UniversityB.Eng. in computer science

From the biography.

  1. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes Stanford University. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes University of Hong Kong. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes University of Hong Kong. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes University of Hong Kong. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Lequan Yu yet. Send us a free-licensed photo.

  1. Lequan Yu yulequan.github.io. Checked 21 October 2026.
  2. [1907.07034] Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation arxiv.org. Checked 21 October 2026.
  3. MHRC Research Seminar: Harnessing Multimodal AI for Knowledge-Enhanced Computational Pathology | PolyU Academy for Interdisciplinary Research (PAIR) polyu.edu.hk. Checked 21 October 2026.
  4. Knowledge-guided adaptation of pathology foundation models effectively improves cross-domain generalization and demographic fairness nature.com. Checked 21 October 2026.
  5. Yu, Lequan ai.hku.hk. Checked 21 October 2026.