My name is Nikhil, and I'm a software engineer at Jane Street. Previously, I did my Bachelor's and Master's in Computer Science at Stanford, where I had the privilege of working with Professors Serena Yeung and Leonidas Guibas. Check out this page to learn more about what I've been working on, and don't forget to connect via the links below!
Current machine learning methods struggle to solve Bongard problems, which are a type of IQ test that requires deriving an abstract “concept” from a set of positive and negative “support” images, and then classifying whether or not a new query image depicts the key concept. In this research project with collaborators at the Stanford AI Lab (SAIL), I explored a few approaches for incorporating cross-image context within Bongard problems in order to obtain improved performance. Our top-performing approach sets a new state-of-the-art on two benchmark Bongard datasets.
