NeurIPS 2024: Our paper “Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors” is accepted to NeurIPS 2024!
About me
I am an assistant professor of Electrical and Computer Engineering at Johns Hopkins University. I hold a joint appointment at the Data Science and Artificial Intelligence (DSAI) Institute.My research focuses on developing advanced algorithms and mathematical foundations for computational imaging. By integrating techniques from machine learning, computer vision, optimization, probability theory, and physics, I aim to create comprehensive frameworks for reliably and interpretably incorporating artificial intelligence (AI) into imaging systems, thereby unlocking novel capabilities that surpass the limitations of traditional methods.
Before joining Johns Hopkins, I was a postdoctoral fellow in the Department of Computing and Mathematical Sciences at California Institute of Technology, working with Prof. Katie Bouman. I earned my Ph.D. at Washingtion University in St. Louis and B.Eng. at Sichuan University. I was fortunate to work with Prof. Ulugbek Kamilov, who taught and helped me a lot in my academic career. I worked as a part-time research specialist at Cedars-Sinai Hospital with Dr. Ouyang on cardiac imaging. I interned at Capacity Inc. and Nvidia Research working on NLP and depth estimation.
Prospective Students: I look for PhD/Master/Undergrad students for multiple exciting projects. If you are interested, please fill this qick form to reach out (preferred & see more info there). You may also send me emails. Due to the large volume of requests, I will not reply to each inquiry.
News
2024
IEEE TCI: My work “Provable Probabilistic Imaging using Score-Based Generative Priors” is accepted to IEEE Transactions on Computational Imaging!
New Paper on arXiv: Our new paper “Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors” is on arXiv!
IEEE TCI: Our work “Learning Task-Specific Strategies for Accelerated MRI” is accepted to IEEE Transactions on Computational Imaging!
2023
New Paper on arXiv: My work “Provable Probabilistic Imaging using Score-Based Generative Priors” is now on arXiv! In this work, I proposed plug-and-play Monte Carlo (PMC) as a principled framework to perform posterior sampling for general imaging inverse problems.
Turner Dissertation Award: Excited to share that my dissertation has won the 2022 Turner Dissertation Award!
2022
Elected as a member of IEEE CI TC: I was elected as a member of IEEE Computational Imaging Technical Committee!
Start at Cedars-Sinai Hospital: I joined the Heart Institute Operations as a part-time Clinical Research Data Speclist.
Nature Machine Intelligence: My paper “Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields” has been accepted to Nature Machine Intelligence.
Start my postdoc at Caltech: I will continue working on computational imaging problems with! Free feel to reach out for discussion and collaboration!
ECCV: Our paper “CURE: Learning Cross-Video Neural Representations for High-Quality Frame Interpolation” has been accepted to ECCV 2022.
2021
IEEE TCI Accepted: Our paper “Scalable Plug-and-Play ADMM with Convergence Guarantees” has been accepted to IEEE Transaction on Computational Imaging.
IEEE TCI Accepted: My co-authored paper “SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees” has been accepted to IEEE Transaction on Computational Imaging.
Nvidia Research: Extemely happy to share that I will join Nvidia as a summer intern in 2021.