Contact Information or
Google Scholar

About Me

I am a Master's student at the University of Toronto where my advisor is Yang Xu. Currently, I am a visiting researcher with Tom Griffiths and the Computational Cognitive Science Lab at Princeton University. I am very fortunate to have my research supported by a Vector Scholarship in Artificial Intelligence.

I have worked on training deep generative models, statistical models of semantic change, and identifying conversational behaviour.


  • Learning Deep Representations by Mutual Information Estimation and Maximization
    R Devon Hjelm, Alex Fedorov, Samuel Lavoie, Karan Grewal, Phil Bachman, Adam Trischler, Yoshua Bengio.
    ICLR 2019.
    [pdf] [slides]
  • Variance Regularizing Adversarial Learning
    *Karan Grewal, *R Devon Hjelm, Yoshua Bengio.
    ICML 2017 workshop on Implicit Generative Models.
    [pdf] [slides]
  • On the Challenges of Detecting Rude Conversational Behaviour
    Karan Grewal, Khai N. Truong.
    Unpublished Report.


alt text

MISE is an intensive summer camp for bright high school students to learn about cutting-edge research in engineering and other sciences. Recently, I was a research mentor at MISE in Ghana where I taught a select group of students about machine learning and its applications to computer security. I hope my efforts will motivate them to one day become leaders in these fields and transform the global R&D landscape.