
Yu Sun joined Johns Hopkins as an assistant professor in the Whiting School of Engineering’s Department of Electrical and Computer Engineering last fall from Caltech. He also holds a joint appointment at the Data Science and Artificial Intelligence (DSAI) Institute.
Sun is at the forefront of advancing computational imaging by integrating AI into imaging systems. In this Q&A, he shares insights into his research, career inspirations, and his vision for the future of computational imaging.
What are your research interests and what specific problem are addressing?
I work in the field of computational imaging—which integrates sensors with algorithms to visualize objects that are not directly visible. One famous example of such is the capture of an image of black hole M87*, in which imaging algorithms combined with radio telescope arrays allow humans to, for the first time in history, see a black hole. My research is centered around the development of advanced algorithms and mathematical foundations for computational imaging. Recently, artificial intelligence has shown great promise in image generation and creation. A specific problem I am recently interested in is to create algorithmic and theoretical frameworks, so that we can integrate these powerful generative AI models into computational imaging with provable reliability, thereby unlocking novel capabilities that surpass the limitations of traditional methods.
What inspired you to pursue a career in electrical and computer engineering, and what excites you most about joining Johns Hopkins?
I’ve always been fascinated by the intersection of mathematics, physics, and engineering. Electrical and computer engineering offers a unique platform to explore these areas through both theory and practice. The idea of using computation to make sense of the world’s complexity—from the signals we process to the images we interpret—drove me to pursue this field. Joining Johns Hopkins is incredibly exciting because of its interdisciplinary culture and reputation for innovation, particularly in biomedicine and engineering. I’m thrilled to collaborate with world-class researchers and students who are passionate about solving real-world problems, and I look forward to contributing to the university’s legacy of advancing knowledge and technology.
What are the biggest challenges and opportunities in your field over the next decade?
One of the biggest challenges in computational imaging is balancing the increasing complexity of machine learning models with the need for explainability and reliability, especially in critical applications in clinics and scientific exploration. While deep learning has achieved remarkable success, its “black box” nature often makes it difficult to trust or interpret results. At the same time, this challenge also offers many opportunities. By integrating imaging physics with machine learning, we can create hybrid frameworks that are both interpretable and powerful. Advances in computational hardware, data availability, and algorithm design will also open doors for solving even more complex problems, such as 3D/4D imaging problems.
Where did you grow up and where did you live before Baltimore and/or the DC area?
I grew up in Shanghai, China, and went to Chengdu, China (the home of giant pandas) for college at Sichuan University. After that, I came to the U.S. and lived in St Louis, MO for about 7 years to complete my master’s and Ph.D. degree at Washington University in St. Louis. Before joining Johns Hopkins, I lived in Pasadena, CA, where I worked as a Computing, Data, and Society Postdoctoral Fellow at Caltech. These experiences have shaped my perspective and approach to research, and I’m excited to bring those insights to this new chapter at Hopkins.
What hobbies or interests do you have outside of academia that help you stay balanced?
Outside of academia, I enjoy reading and hiking. I also love exploring new cities and cultures. I’m looking forward to discovering Baltimore!