Yash Patel

I’m currently a 3rd year PhD student at the University of Michigan studying Statistics advised by Ambuj Tewari. I am interested in machine learning and its applications to computational biology, specifically 3D heterogeneous reconstruction of proteins from Cryo-EM images. I’ve also dabbled in conformal prediction, variational inference, and generative models.

I previously worked as a computer vision/graphics engineer at Facebook, where I worked on realtime dense 3D reconstruction (point clouds/KinectFusion) and dynamic real-time disocclusion on meshes. I previously worked on the software for the Manifold camera, specifically adding support for rendering on cloud farms and improving the efficiency of the depth estimation algorithm. I also implemented, trained, and optimized (with layer fusion, SNPE, and QAT quantization) an end-to-end deep learning-based feature for Portal to run at realtime on the Snapdragon SoC.

I graduated as a Math major from Princeton in 2018 (certificates in CS and Statistics/ML). I also really enjoy lifting, biking, climbing, and reading books and papers.

See my full (probably outdated) resume here. Some projects I have worked on (see other tabs for full lists):

Projects:

• Intertect
• Neuropath
• MIS Ray Tracing
• Hyperloop Pod

Research:

• Deanonymizing Bitcoin Transactions
• FairTear