Jiayun (Peter) Wang is an Assistant Professor in the School of Computational Science and Engineering (CSE), College of Computing, at the Georgia Institute of Technology, where he leads the Science, World Models, and Intelligence (SWI) Lab. His research lies at the intersection of machine learning, computer vision, and AI for science and healthcare, emphasizing physically and geometrically precise models. He develops generative and multimodal models, self-supervised visual representations, neural operators for inverse problems and simulation, and self-improving agentic systems. His work spans robust perception and world modeling, with applications including MRI reconstruction, ultrasound and photoacoustic imaging, clinical diagnosis, and surgical training. Before joining Georgia Tech in 2026, he was a senior machine learning scientist at Accenture an a postdoctoral researcher at Caltech. He earned his Ph.D. from UC Berkeley in 2023 and a bachelor's degree from Xi'an Jiaotong University in 2018. His research received Best Paper Awards at Machine Learning for Health in 2023 and 2024.
- AI/ML for Health and Life Sciences
- Foundations of AI/ML
- Physics-aware generative and world models;
- Self-supervised 3D vision and pose learning
- Geometric representation learning;
- Neural operators and inverse problems
- Multimodal foundation models;
- Agentic AI and model optimization