I am a PhD candidate at Caltech, where I am very fortunate to be advised by Yisong Yue and to work closely with Yang Song. My research centers on generative modeling — in particular, inference-time posterior sampling with pretrained diffusion priors, with applications to reward-guided generation and inverse problems. More recently, I have been exploring the interplay between generative modeling and representation learning, with a focus on learning better visual tokenizers for generative models.

Outside of research, I enjoy chess, piano, photography, and running.