I am a CS PhD student at 
Georgia Tech
working with Yalong Yang and Polo Chau.
My research explores how spatial computing techniques, grounded in HCI principles, can reshape the way we analyze and interpret multi-dimensional data. I focus on designing immersive visualizations and cross-reality systems that bridge the physical and virtual worlds, enabling more intuitive, interactive, and collaborative approaches to data exploration.
Through my work, I've had the opportunity to collaborate with researchers, developers, designers, and
scientists from 
JPMorgan Chase, 
Adobe, 
Goldman Sachs,
Duke
University, and 
Children’s Healthcare of Atlanta.
CrossAtlas is a cross-reality collaboration platform that helps users share and understand spatial references across VR and desktop environments using synchronized VR-PC views, bidirectional projection techniques, and shared spatial landmarks.
ComplicitSplat is the first black-box attack on downstream object detectors using 3D Gaussian Splatting. It exploits view-dependent spherical harmonics to conceal camouflages at targeted viewpoints, fooling detectors across synthetic and real-world scenes without model access.
LitForager is an immersive sensemaking system for literature exploration that visualizes academic papers as a 3D network, enabling researchers to explore, organize, and synthesize literature through multimodal interactions like gesture and voice.
Diffusion Explainer is the first interactive visualization tool that explains how Stable Diffusion turns text prompts into images. It integrates a visual overview of Stable Diffusion’s components with interactive widgets explaining their operations.
DiffusionDB is the first large-scale text-to-image prompt dataset containing 14 million images generated by Stable Diffusion. It provides exciting research opportunities in evaluating generative models, detecting deepfakes, and designing interaction tools.
Argo Scholar is an interactive literature exploration visualization system that runs in your web browsers. It allows researchers to incrementally visualize literature networks with interactive force-directed layout and save and publish via URLs.
CardiacAR is an iOS Augmented Reality application that enables users to perform interactive surgical planning on mobile devices, offering omni-directional slicing of patients’ 3D heart models and virtual annotation to assist planning.