I'm happy to share some of the work I've been doing at Lime recently. Mainly collaborating with Yi Su (and with the help of many other co-workers) we were able to train and deploy a computer vision based model to detect whether a scooter is parked in compliance or not through the photos at the end of a trip or scooter deployment. As proper parking is one of the major factors in winning RFPs and the ability to operate in cities, I'm glad that our model can help nudge users to park better and make…

Below is a series of summaries of my research in cryptography while I was a student at MIT.

During the Spring 2018 Semester, I took Vinod Vaikuntanathan and Shafi Goldwasser's Cryptography & Cryptanalysis (6.875) class. I filmed all but one lecture (oops I lost the video on MPC somwhere in the middle of class), providing a resource for current and future students to access the wonderful lectures. You can view the playlist here. The first recorded lecture is embedded below.

For our final project for the Distributed Systems Class at MIT (6.824), we have successfully implemented a command line interface text editor, such that multiple clients can collaborate on a single document and attain eventual consistency in the document through the use of operational transforms.

Our goal is to explore models for language learning (in this case learning numerical digits in their spoken and visual representations) in the manner that humans learn languages as children. Namely, children do not have intermediary text transcriptions in corresponding visual and audio inputs from the world around them; rather, they directly make connections between what they see and what they hear. In this paper, we construct models for the direct bi-directional classification of speech and…

During the Spring 2016 Semester, I took Ankur Moitra's Advanced Algorithms (6.854) class. With the help of my friends Sitara Persad and Shraman Ray Chaudhuri, we filmed all but two lectures, providing a resource for current and future students to access Prof. Moitra's wonderful lectures. You can view the playlist here. The first recorded lecture is embedded below.