|
I am a research scientist in the Fundamental AI Research (FAIR) division of Meta AI. In addition to my role at FAIR, I also spend time at UC Berkeley as a visiting researcher, hosted by Prof. Pieter Abbeel. My research focuses on building foundation models for all manner of Embodied AI agents operating in the open world, such as smart glasses and robots. Relevent topics include self-supervised representation learning, sequence models for decision making, and offline RL. Previously, I was a research scientist and visiting researcher at CMU mentored by Prof. Abhinav Gupta. I recieved my PhD in Computer Science from the University of Washington working with Profs. Sham Kakade and Emo Todorov. During this time, I also worked closely with Sergey Levine and Chelsea Finn, and spent time as a student researcher at Google Brain and OpenAI. Before that, I recieved my Bachelors degree along with the best undergraduate thesis award from IIT Madras. | |
|
Representative Papers
Foundation Models for Embodied AI VC-1: Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence? R3M: A Universal Visual Representation for Robot Manipulation Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?
Sequence Models for Reinforcement Learning Masked Trajectory Models for Prediction, Representation, and Control Decision Transformer: Reinforcement Learning via Sequence Modeling
Tools for Robotics RoboHive: A Unified Framework for Robot Learning Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations | |
|
Mentoring I enjoy collaborating with a diverse set of students and researchers. I have had the pleasure of mentoring some highly motivated students at both the undergraduate and PhD levels. List of current students and alumni. | |
|
|
|
Teaching
CSE599G: Deep Reinforcement Learning (Instructor)
CSE547: Machine Learning for Big Data (Teaching Assistant)
CSE546: Machine Learning (Teaching Assistant) | |
|