Ph.D. Student, Stanford University
I'm a second-year Ph.D. student at the Stanford Physical and Spatial Intelligence Lab, advised by Prof. Gordon Wetzstein.
I study the fundamentals and applications of diffusion models, from fundamentals for efficient generation to long-context generation, causal video generation, and physical AI.
Previously, I worked on single-photon imaging with Prof. Kyros Kutulakos and Prof. David Lindell.
Spectral Progressive Diffusion framework that grows resolution along the denoising trajectory of pretrained models for efficient, high-quality image and video generation.
We introduce a real-time, task-aware foveated imaging framework that learns a sensor attention policy to dynamically allocate pixel bandwidth, extensively validated in simulation and on a 200-megapixel prototype.
A human-centric framework for efficient image and video generation while preserving perceptual quality.
An approach that uses single-photon cameras to harvest ambient light in our environment, such as those from asynchronous pulsed lidar systems, for passive 3D vision.
We study homeomorphisms of the circle that are smooth diffeomorphisms away from a finite set of n points.
