I'm a first-year CS PhD student at Stanford! Prior to that, I spent the summer as a research intern at Physical Intelligence. If you're reading this and interested in the areas I work on, I always love to meet new people—drop me a message!.
Previously, I was a Master's of Robotics student at CMU, advised by Katerina Fragkiadaki and working with Deepak Pathak. Before that, I did my undergrad in Computer Science at UCLA1, where I was fortunate to be advised by Bolei Zhou.
Graduated summa cum laude (top 5%). During my undergrad, I was a research intern under Raquel Urtasun at Waabi. Prior to that, I did internships at both DoorDash and at The Aerospace Corporation.
This site mainly exists to hold my CV, contact info, and my recent projects. If you want to take a look at some of my code, please see my GitHub profile. Outside of research, I love to spend time outdoors.
Dynamic Dust3r Large-scale data generation of dynamic scenes in Blender, based off a combination of PointOdyssey and Kubrics. This provides pixel-perfect GT 3D point tracking which is used to fine-tuning dust3r to predict the static pointmap in one camera frame and a dynamic pointmap delta in the second camera frame, enabling tracking and reconstruction of dynamic scenes. model code / datagen code
Interpertable image editing with latent objects We develop an image editing pipeline trained an unlabeled image collection. We train a diffusion model to decode a set of region features obtained from a off-the-shelf encoder & segmentation model. By heavily augmenting the denoising target and using contrastive losses, we learn a latent bottleneck that allows for positional and semantic control for individual objects in a given image. code and visualizations
Design taken from Jon Barron's website. | To see some 🔮, load this page while disconnected from the internet.
