Ashish Kumar

alt text 

Ph.D. Student, EECS U.C. Berkeley

I am a graduate student at UC Berkeley advised by Prof. Jitendra Malik. Before coming here, I was a Research Fellow at Microsoft Research India, where I worked with Dr. Manik Varma and Dr. Prateek Jain on developing Resource Efficient Machine Learning algorithms. I am broadly interested in Robotics, with a focus on developing efficient deployable algorithms for navigation. I completed my undergraduate study at Indian Institute of Technology Jodhpur, with a major in Computer Science and Engineering. My Bachelor's Thesis was advised by Dr. Gaurav Bhatnagar.

You can reach me at :

Here is my Resume.


  • “Learning Navigation Subroutines from Egocentric Videos”
    Ashish Kumar, Saurabh Gupta, Jitendra Malik.
    Conference on Robot Learning. 2019
    [Pdf] [Webpage] [Code]

  • “Visual Memory for Robust Path Following”
    Ashish Kumar* , Saurabh Gupta*, David Fouhey, Sergey Levine, Jitendra Malik.
    Oral Presentation at Neural Information Processing Systems. 2018
    [Pdf] [Webpage]

  • “FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network”
    Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma.
    Neural Information Processing Systems. 2018
    [Pdf] [Code]

  • “Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things”
    Ashish Kumar, Saurabh Goyal, and Manik Varma.
    International Conference on Machine Learning. 2017.
    [Abstract] [Pdf] [Code]

  • “ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices”
    Chirag Gupta, Arun Sai Suggala, Ankit Goyal, Harsha Vardhan Simhadri, Bhargavi Paranjape, Ashish Kumar, Saurabh Goyal, Raghavendra Udupa, Manik Varma, and Prateek Jain.
    International Conference on Machine Learning. 2017.
    [Abstract] [Pdf] [Code]


  • Amazon Research, Palo Alto on “The Edge of Machine Learning” (Sept, 2017)

  • Facebook AI Research, Menlo Park on “The Edge of Machine Learning” (Sept, 2017)

  • Microsoft Research on “The Edge of Machine Learning” (Cambridge - April, 2017 and Redmond - November, 2017)

  • Oxford University, UK on “The Edge of Machine Learning” (April, 2017)



I have been fortunate enough to work with the following people (reverse chronological order):


alt text 

Scuba Diving at Great Barrier Reef, Australia 2017
Depth: 10 meters

<– Scuba Diving at Phuket, Thailand in 2016
Depth: 12 meters

alt text 

<– Bungy Jumping at Rishikesh, India in 2016
Height: 83 meters