I am a PhD student in Computer Science at Stanford University, where I work at the intersection of machine learning, computer vision, and robotics. Specifically I am interested in problems relating to multi-task learning, hierarchical reinforcement learning, and perception for robotics. I am co-advised by Professors Chelsea Finn and Silvio Savarese, and am funded by the National Science Foundation Graduate Fellowship.

I completed my Bachelors in Computer Science at the California Institute of Technology (Caltech), where I worked with Yisong Yue on multi-agent reinforcement learning. In the past I have worked at Google Brain and General Electric Current.

Github | CV | Google Scholar | Twitter


  • Our work on one-shot visual imitation Neural Task Graphs accepted for Oral presentation at CVPR 2019
  • Time Reversal as Self-Supervision with Google Brain accepted to NeurIPS Deep RL Workshop
  • Awarded the 2018 National Science Foundation Graduate Research Fellowship
  • Our work Neural Task Programming is accepted to ICRA 2018


Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation
Suraj Nair, Chelsea Finn
[arxiv] [website]

Time Reversal as Self-Supervision
Suraj Nair, Mohammad Babaeizadeh, Chelsea Finn, Sergey Levine, Vikash Kumar
Deep Reinforcement Learning Workshop, NIPS 2018
[arxiv] [website]

Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstrations
De-An Huang*, Suraj Nair*, Danfei Xu*, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, Juan Carlos Niebles
CVPR 2019 (Oral)

Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
Danfei Xu*, Suraj Nair*, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese
ICRA, 2018
[arxiv] [website] [video] [Two Minute Papers]

Reliable Real-time Seismic Signal/Noise Discrimination with Machine Learning
Men-Andrin Meier, Zach Ross, Anshul Ramachandran, Ashwin Balakrishna, Suraj Nair, Peter Kundzicz, Zefeng Li, Egill Hauksson, Jennifer Andrews
Machine Learning for Geophysical & Geochemical Signals Workshop, NIPS 2018

Annotated Reconstruction of 3D Spaces Using Drones
Suraj Nair, Anshul Ramachandran, Peter Kundzicz
IEEE MIT URTC, 2017, Best Paper Presentation


Research Intern
June 2018 - September 2018 | Mountain View, CA
Google Brain

Visiting Researcher
June 2017 - December 2017 | Stanford, CA
Stanford Vision and Learning Lab

Machine Learning Consultant
March 2017 - September 2017 | Los Angeles, CA

Student Researcher
April 2016 - June 2018 | Pasadena, CA
Decision, Optimization, and Learning at California Institute of Technology

Software Development Intern
June - Sept 2016 | Mountain View, CA
General Electric, Current by GE

Software Engineering Intern
June - Sept 2015 | Mountain View, CA
KloudData Inc.