Katherine Xu

I'm a first year CS PhD student at the University of Pennsylvania GRASP Lab, where I'm fortunate to be advised by Professor Jianbo Shi. My research interests center around generative models, scene understanding, and multimodal learning.

I completed my bachelor's and master's in Computer Science with a minor in Mathematics at MIT, where I worked with multiple research groups at MIT CSAIL, MIT Quest for Intelligence, and MIT Environmental Solutions Initiative. I have also had the pleasure of interning at Meta for two summers and at the Honda Research Institute.

Email  /  Twitter  /  LinkedIn  /  Github

profile photo
Research
sym Chemistry Insights for Large Pretrained GNNs
Katherine Xu, Janice Lan
NeurIPS AI for Science Workshop, 2022

During my internship at Meta AI, I worked on the Open Catalyst team led by Dr. Larry Zitnick that uses AI to discover catalysts for renewable energy storage. We present perturbation analyses of graph neural network predictions on the Open Catalyst dataset to understand whether the model predictions align with chemical intuition.

sym A Novel Digital Algorithm for Identifying Liver Steatosis Using Smartphone-Captured Images
Katherine Xu*, Siavash Raigani*, Angela Shih, Sofia G. Baptista, Ivy Rosales, Nicola M. Parry, Stuti G. Shroff, Joseph Misdraji, Korkut Uygun, Heidi Yeh, Katherine Fairchild, Leigh Anne Dageforde (* equal contribution)
Transplantation Direct, 2022

sym Linking Threat Tactics, Techniques, and Patterns with Defensive Weaknesses, Vulnerabilities and Affected Platform Configurations for Cyber Hunting
Erik Hemberg, Jonathan Kelly, Michal Shlapentokh-Rothman, Bryn Reinstadler,
Katherine Xu, Nick Rutar, Una-May O'Reilly

Projects
sym Rendering and Extracting Transparent Objects using TensoRF and Feature Field Distillation
MIT Machine Learning for Inverse Graphics
Website  /  Code

sym Object Recognition for Selective Clutter Clearing using PointCLIP
MIT Robotic Manipulation
Paper

sym Lyric and Audio-Based Music Video Generation
MIT Advances in Computer Vision
Code


     


Template credit to Jon Barron.