Research πŸ”¬

My research has mainly been focused on computer vision, a subfield of artificial intelligence 🧠 that aims to create programs that enable computers to πŸ‘οΈ "see" like humans. I have been lucky enough to work with lots of amazing researchers from around the world πŸ‡ΊπŸ‡ΈπŸ‡¨πŸ‡¦πŸ‡¬πŸ‡§. Below is a sample of what we have accomplished together.Β 

Data Centric AI on a Massive Scale

The success of machine learning is a generalized algorithm which picks up patterns in the data. Instead of hand crafting programs to make the software intelligent, the computer is able to learn this on its own. The resulting algorithms are only as good as the data (garbage in, garbage out). The training dataset needs to adequately represent the inputs the model will see out in the wild. DataComp is a data-centric competition which flips the traditional way of incrementally improving AI algorithms on its head: instead of fixing the training dataset and iterating on the model architecture, participants are given a fixed model and find ways to improve the training dataset. We scraped vast portions of the internet to create a large pool of images and captions that participants can try their filtering methods on, as well as bringing their own data. This was a large scale project with lots of collaborators from UW, Apple, Google, AI2, Stability.AI and more. Check out the website, code, and paper to learn more.Β 

General Purpose AI

GRIT tests the versatility of computer vision systems and sets a shared goal for researchers working on the next generation of AI models. Check out the website, paper, and CVPR talk (timestamp).Β 

Private ML

In sensitive applications such as healthcare or banking, privacy is paramount, preventing the development of data hungry models. I evaluated the usability of privacy preserving machine learning tools.


Smart Photos

To capture better photos, it is helpful to respond to the lighting and materials in a scene. We created a dataset to train such models. Check out the website, paper (ICCV 2019), and video below.Β 


Fast Physics

Efficiently compressing physics simulations speeds up visual effects pipelines. I procedurally generated the 3D scenes used for testing this method. Check out the website, paper (SCA 2018) , and video below.Β 

Perceptual Grouping

One approach to making computers "see" like humans is to leverage our interdisciplinary understanding of the human vision system (psychology, biology, and optics) to design systems that mimic properties that we observe in humans. For example, I have trained a neural network to classify textures as a human would. Additionally, we have created a system that responds to optical illusions by "filling in gaps" similar to way a human does. Check out the website, paper (BMVC 2021), and presentation below. Β