Dishank Bansal

dishankbansal09@gmail.com

Namaste! Bonjour! I am currently an AI resident at Meta AI (FAIR) working with Brandon Amos, Ricky Chen and Mustafa Mukadam. My current research vision is to enable RL agents to generalize across tasks on the same system without re-training for each tasks individually. Before this, I was a :mortar_board: MSc Student in Computer Science at Mila and University of Montreal where I worked on robot learning at Robotics and Embodied AI Lab under supervision of Prof. Liam Paull.

Before joining as Master’s student, I was an intern for a year under Prof. Liam Paull. Before that I was undergraduate student at IIT Kharagpur, where I spent all of my time at AGV under supervision of Prof. Debashish Chakravarty working on perception and embbeded-control systems for autonomous vehicles.

I am a avid chess and badminton player (not professionally).

News

Jul 1, 2023 :page_facing_up: Our TaskMet paper got accepted at DiffAE Workshop, ICML 2023.
Aug 1, 2022 :page_facing_up: Started AI Residency at Meta AI (FAIR) working on reinforcement learning.
Jan 1, 2022 :page_facing_up: Our f-cal paper got accepted at ICRA 2022.
Dec 1, 2021 :trophy: Granted thesis writing scholarship by Department of Computer Science and Operations Research, UdeM.
Sep 1, 2020 :mortar_board: Starting MSc at Mila under Prof. Liam Paull

Selected Publications

  1. f-Cal: Calibrated aleatoric uncertainty estimation from neural networks for robot perception
    Bhatt, Dhaivat, Mani, Kaustubh, Bansal, Dishank, Murthy, Krishna, Lee, Hanju, and Paull, Liam
    IEEE International Conference on Robotics and Automation 2022
  2. Probabilistic Object Detection: Strengths, Weaknesses, Opportunities
    Bhatt, Dhaivat*, Bansal, Dishank*, Gupta, Gunshi*, Lee, Hanju, Jatavallabhula, Krishna Murthy, and Paull, Liam
    AIAD Workshop, ICML 2020
  3. TaskMet: Task-Driven Metric Learning for Model Learning
    Bansal, Dishank, T.Q. Chen, Ricky, Mustafa, Mukadam, and Amos, Brandon
    Differentiable Almost Everything Workshop, ICML 2023