Zeyu Gao

Zeyu Gao

Research Associate

About Me

I am a postdoctoral researcher in the Department of Oncology at the University of Cambridge, affiliated with the Crispin Lab at the CRUK Cambridge Centre and the Early Cancer Institute. My current research is funded by GE Healthcare. I am also a Postdoctoral Fellow of Trinity College, University of Cambridge.

I received my Ph.D. in Computer Science from Xi’an Jiaotong University in 2023, where I was jointly trained by the School of Computer Science and the School of Mathematics and Statistics, under the supervision of Prof. Chen Li and Prof. Deyu Meng. Before that, I obtained my M.S. degree from the School of Artificial Intelligence, Xidian University, under the supervision of Prof. Xiangrong Zhang.

Research

My current research focuses on computational pathology, specifically on the development and application of machine learning and deep learning models to extract clinically relevant information from histopathological images, thereby improving the accuracy of cancer diagnosis and treatment prediction.

My work involves the analysis of pathological images across multiple scales and leverages a range of learning paradigms—including semi-supervised learning, multi-instance learning, contrastive learning, vision-language models, and diffusion models to tackle various challenges in computational pathology.

Education

  • Xi’an Jiaotong University, Ph.D. in Computer Science [Sept 2019 – June 2023]
    • Thesis: Research on Deep Learning Method for Multi-level Tasks of Pathological Image Analysis

  • Xidian University, M.S. in Artificial Intelligence [Sept 2014 – June 2017]

  • Xidian University, B.S. in Electronic Engineering [Sept 2010 – June 2014]

Selected Honors & Awards

  • Postdoc Fellow, Trinity College, University of Cambridge, 2024-2026
  • Excellent Postgraduate of Xi’an Jiaotong University 2021-2022.
  • MICCAI Student Travel Award, 2021.

Recent news and activities

  • [Aug. 2025] Proud to share that this important project (which I supervised), “StaDis: Stability distance to detecting out-of-distribution data in computational pathology”, has been accepted by Medical Image Analysis! A key step toward robust and reliable OOD detection in computational pathology!
  • [Aug. 2025] Honored to give an invited lecture on “Multiomics for Cancer” at the Oxford ML School 2025, Oxford, UK.
  • [Jul. 2025] Proud to share that this impactful dataset project (which I supervised), “A fully annotated pathology slide dataset for early gastric cancer and precancerous lesions” has been accepted by Nature Scientific Data! An important resource for computational pathology and early gastric cancer research!
  • [Jul. 2025] Proud to share that the first project I’ve supervised at University of Cambridge, “CoxKAN: Kolmogorov–Arnold Networks for interpretable, high-performance survival analysis”, has been accepted by Bioinformatics! Nearly a year in the making, and already 15 citations on arXiv!
  • [Jun. 2025] Our special issue “Can AI Care? Affective LLMs for the Future of Mental Health” is now live on IEEE Transactions on Affective Computing. The issue aims to explore how large language models can support mental health through affective computing. Submissions are now open here.
  • [Jun. 2025] Honored to give an invited lecture on “Multimodal and Multiomics Foundation Models” at the Artificial Intelligence in Cancer Research Summer School 2025, Corfu, Greece.
  • [May. 2025] Delighted to present a poster on “ALPaCA: Adapting Llama for Pathology Context Analysis” at the Artificial Intelligence for Oncology Conference, Milan, Italy.
  • [Apr. 2025] Presented a poster entitled “Bridging whole slide images and large language model for slide-level question answering” at the AACR Annual Meeting 2025, Chicago, US.
  • [Oct. 2024] Gave a flash talk and presented a poster on “Accurate Spatial Quantification in Computational Pathology with Multiple Instance Learning: SMMILe” at the CRUK CI/CC Retreat 2024, Cambridge, UK.
  • [Jul. 2024] Invited to speak on “Accurate Spatial Quantification and WSI Classification with Measurable Multi-Instance Learning” at the ICM Symposium 2024, Cambridge, UK.
  • [Jun. 2024] Honored to give an invited talk on “Measurable Multi-Instance Learning for Cancer Classification and Spatial Quantification” at the C2D3 Computational Biology Annual Symposium 2024, Cambridge, UK.
  • [Jan. 2024] Organized the workshop “Integrating Deep Learning with Pathology for Cancer Diagnosis and Research” at the Cambridge University Oncology Society Annual Conference 2024, Cambridge, UK.