A PhD student at Caltech in CMS interested in generative models, working with Katie Bouman, Yisong Yue, and Yang Song
DAPS. [CVPR 2025 Oral] Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
STeP. STeP: a general and scalable framework for solving video inverse problems with spatiotemporal diffusion priors