Aravind Rajeswaran

Aravind Rajeswaran

Research Scientist at Microsoft AI Frontiers

Agents Reinforcement Learning World Models Multimodal Learning Robotics

I'm interested in building AI agents that can perceive, think, and act like humans in the open world, both digital and physical! For this, I lean on RL, world models, and visual imitation. I'm now at Microsoft AI Frontiers building on-device computer use agents like Fara. Prior to this, I spent 4 years at Meta (FAIR) working on Embodied AI agents with Jitendra Malik, Dhruv Batra, and Abhinav Gupta. I also collaborated closely with Prof. Pieter Abbeel at UC Berkeley as a visiting researcher.

I received my PhD in Computer Science from the University of Washington working with Profs. Sham Kakade and Emo Todorov. 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 received my bachelors and the best undergraduate thesis award from IIT Madras working with Balaraman Ravindran.

Selected Research

Fara-7B computer use agent

Fara-7B: An Efficient Agentic Model for Computer Use

CUA Team @ Microsoft AIF (Role: Led Visual Grounding)

Preprint 2024 | Open-Weight Model Release

Paper Model Blog
OpenEQA benchmark

OpenEQA: Embodied Question Answering in the Era of
Foundation Models

Cortex Team @ FAIR (PI and Project Lead)

CVPR 2024

Project
VC-1 visual cortex for embodied AI

VC-1: Where Are We in the Search for an Artificial Visual
Cortex for Embodied Intelligence?

Cortex Team @ FAIR (PI and Tech Lead)

NeurIPS 2023

Project
Decision Transformer

Decision Transformer: Reinforcement Learning via
Sequence Modeling

Lili Chen*, Kevin Lu*, Aravind Rajeswaran, et al.

NeurIPS 2021

Project
Dexterous manipulation with deep RL

Learning Complex Dexterous Manipulation with Deep RL
and Demonstrations

Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, et al.

RSS 2018

Project
See all publications on Google Scholar

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.

PhD Interns

University Students & AI Residents

Teaching

CSE599G: Deep Reinforcement Learning Instructor

I designed and co-taught a course on deep reinforcement learning at UW in Spring 2018. The course presents a rigorous mathematical treatment of various RL algorithms along with illustrative applications in robotics. Deep RL courses at UW, MIT, and CMU have borrowed and built upon the material I developed for this course.

CSE547: Machine Learning for Big Data Teaching Assistant

This is an advanced graduate level course on machine learning with emphasis on machine learning at scale and distributed algorithms. Topics covered include hashing, sketching, streaming, large-scale distributed optimization, federated learning, and contextual bandits. I was the lead TA for this class.