Yu Guang Wang

Yu Guang Wang is an Associate Professor at Shanghai Jiao Tong University, holding positions across multiple institutes including the Institute of Natural Sciences, School of Mathematical Sciences, Department of Computer Science and Engineering, and AI Biomedicine Center of Zhangjiang Institute for Advanced Study. He also serves as Adjunct Associate Professor at both UNSW Sydney and Shanghai AI Laboratory, demonstrating his significant interdisciplinary reach.

His research spans artificial intelligence, computational mathematics, statistics, and data science, with particular focus on geometric deep learning, graph neural networks, applied harmonic analysis, and Bayesian inference. His work bridges theoretical foundations with practical applications in biomedicine and protein design, creating impactful connections between mathematics and real-world problems.

Wang's publication record shows a clear progression toward increasingly sophisticated applications of geometric deep learning, particularly in graph neural networks for protein engineering and biomedical applications. His recent work demonstrates strong interdisciplinary collaboration, combining topological data analysis with machine learning for complex biological systems.

• ICERM Semester Postdoctoral Fellowship of Brown University (2018)
• IPAM visitor of UCLA (2019)
• Long-term visitor of AI Group of Prof Pietro Lio at University of Cambridge (2022)
• ICML Top Reviewer (2020)
• University International Postgraduate Award, UNSW (2011-2015)

As an advisor, Wang has successfully mentored multiple PhD and Master's students working on graph neural networks, geometric deep learning, and applications to biomedicine. His research has been supported by prestigious funding from Shanghai Jiao Tong University, Huawei Central Research Institute, Ministry of Education Key Lab in Scientific and Engineering Computing, Shanghai National Center for Applied Mathematics, National Natural Science Foundation of China, and the European Research Council. He leads an active research group focused on geometric deep learning and its applications to science and medicine.