I am a graduate student at UMass Amherst, majoring in Computer Science. Currently I am advised by Prof. Hao Zhang at Human Centered Robotics Lab, where I work on intersection of computer vision and natural language for Robotics. Prior to this I was advised by Shane Moon, Andrea Madotto of Meta Reality labs and Jay-Yoon Lee of IESL in areas of multi-modal video understanding with special focus on ego centric videos.

My current interests lie at the intersection of vision and language, and my research focuses on using information from multiple sources such as text, images, and video to improve commonsense reasoning capabilities of machines.

In the past, I worked as Head of Product Development for RenderPub, India, and I have interned at Vertica.

Email  /  CV  /  Github /  Linkedin

profile photo