I am an Assistant Professor in the Electrical and Computer Engineering (ECE) department at Rice University. My group advances the efficiency and reliability of learning algorithms for signal representation and generation, particularly for real-world applications such as medical imaging, environment monitoring, and 3D scene reconstruction. I am also a member the Rice Digital Health Initiative and Houston Methodist-Rice Digital Health Institute.
I completed my PhD at MIT CSAIL advised by John Guttag and Frédo Durand, and my postdoctoral research under Bill Freeman. I completed my B.S. degrees in Computer Science and Computer Engineering at the University of Michigan, Ann Arbor.
MetaSeg just won the Best Paper Award at MICCAI! We offer a completely new way to perform medical image segmentation using INRs with 90% fewer parameters than standard models.
Our method WassDiff -- a state-of-the-art generative model for precipitation downscaling -- was just accepted at IEEE Transactions on Geoscience and Remote Sensing.
Presented our paper Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models at ICCV 2025. An interesting analysis on how vision foundation models yield unstable inferences given certain object viewpoints.