I'm a Cornell undergrad advised by Kevin Ellis and Steve Marschner. I'm interested in which levels of abstraction are most useful for building world models, including hybrid neuro-classical simulators and abstract internal models for embodiment.
I'm an incoming CS PhD student at Stanford (Fall 2026)!
See my Google Scholar for the most up-to-date publication list.
Implements Anisotropic Elastoplasticity for Cloth, Knit and Hair Frictional Contact [C. Jiang et. al., 2017].
Implements PBD solver with ability to simulate cloth, volumetric meshes, and fluids in the same solver.
Implementation of the Moving Least Squared Material Point Method, CPIC, various materials, and mesh extraction in 2D and 3D.
Modifies Gaussian Splatting to remove obstructions blocking the view of objects of interest in 3D scene reconstruction.
A path tracer featuring distributive ray tracing, reflections, refractions, volumetrics, emissive objects, and a BVH.
Automates generation of node-edge graph programs from sketches using vision-language models and differential evolution.
Implements "Image-Space Modal Bases for Plausible Manipulation of Objects in Video", extending it with modal warping. Features a Python pipeline and custom JS rasterizer.
Teaching Assistant for undergraduate computer graphics course covering rendering, modeling, and interactive graphics.
Teaching Assistant for introductory programming course covering Java, object-oriented design, and fundamental data structures.
