Sheng Wang

Timeline

1. 2009–2021

   Degrees and Stanford training

   At Peking University, he earns a B.S. in computer science in 2013 with Ming Zhang as his advisor; at the University of Illinois at Urbana-Champaign, he completes a Ph.D. in computer science in 2018 with ChengXiang Zhai and Jian Peng, writing a thesis on leveraging knowledge networks for precision cancer therapy. From August 2018 to January 2021, he works as a postdoctoral researcher at Stanford School of Medicine with Russ Altman.

2. January 2021

   Joining the Allen School

   In January 2021, he joins the Allen School after a postdoctoral appointment at Stanford School of Medicine. His research focuses on high-performance, interpretable AI for biomedical research and health care.

3. 2021

   Open-world cell classification

   In 2021, he develops open-world classification models that generalize to new biomedical tasks without human annotations. Biologists use the approach to classify millions of single cells into thousands of novel cell types, most without annotated examples.

4. 2024

   GigaPath for whole-slide pathology

   In 2024, he and his team develop GigaPath, a foundation model for whole-slide pathology. It achieves state-of-the-art performance on 25 of 26 tasks and applies across different cancer types.

5. December 2025

   GigaTIME for tumor modeling

   In December 2025, he coauthors the study introducing GigaTIME, a multimodal AI model that translates routine H&E pathology slides into virtual multiplex immunofluorescence images. Trained on 40 million cells with paired H&E and mIF images across 21 protein channels, the model supports tumor immune microenvironment research across 14,256 patients, 24 cancer types and 306 subtypes.

6. As of October 2026

   Assistant professor at UW

   As of October 2026, he is an assistant professor in the School of Computer Science and Engineering at the University of Washington. He focuses on large-scale models for biomedical applications, including digital pathology, medical imaging foundation models, chromatin structure prediction and genomics-based drug discovery; his group develops generative AI methods for biomedical imaging and chromatin structure prediction.