Hello!

I am Jyothish Pari, Jyo for short, a first year PhD student at MIT EECS. In my free time, I like biking, learning math, catching (and releasing) insects, folding origami, and racing (virtually). Currently, I am working on the Deep Learning architecture research and optimization with my advisor, Pulkit Agrawal. Previously at NYU, I worked with Lerrel Pinto on robot learning. 

Google Scholar

Publications / Preprints

• Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations
  Siddhant Haldar*, Jyothish Pari *, Anant Rai, Lerrel Pinto
  RSS 2023 (Best Student Paper Award)
  [Arxiv] [Website] [Code]
• The Surprising Effectiveness of Representation Learning for Visual Imitation
  Jyothish Pari *, Nur Muhammad (Mahi) Shafiullah *, Sridhar Pandian Arunachalam, Lerrel Pinto
  RSS 2022
  [Arxiv] [Website] [Code]
• Playful Interactions for Representation Learning
  Sarah Young, Jyothish Pari, Pieter Abbeel, Lerrel Pinto
  IROS 2022
  [Arxiv] [Website]
• Train Offline, Test Online: A Real Robot Learning Benchmark
  G. Zhou *, V. Dean *, M. Srirama, A. Rajeswaran, J. Pari, K. Hatch, A. Jain, T. Yu, P. Abbeel, L. Pinto, C. Finn, A. Gupta
  ICRA 2023
  Workshops: NeurIPS 2022 DeepRL, CoRL 2022 PRL (Spotlight), NeurIPS 2022 WBRC (Best Paper Award), NeurIPS 2022 Offline RL
  [PDF] [Website] [Code]
• A Semi-Automated Computational Approach for Infrared Dark Cloud Localization
  Jyothish Pari, Joseph L. Hora
  Publications of the Astronomical Society of the Pacific 132 (1011), 054301 2020
  [Arxiv] [Code]
• Utilizing Priors to Guide Exploration
  Jyothish Pari, Denis Yarats, Lerrel Pinto
  [PDF]