About Me

  • I am a PhD student at Mila advised by Prof. Sarath Chandar. My research focuses on understanding how deep learning models work, both empirically and theoretically, and discovering better ways to train them. My main area of work is in long-term dependence modelling and memory augmented neural networks, with a particular focus on understanding the use of memory in deep learning models and how to leverage it for better adaptation to distributional shifts in tasks and data.
  • Prior to graduate school, I spent time in the Bay Area working as a data engineer. Before that, I recieved bachelor degrees in Computer Science and Mathematics from the University of Waterloo.
  • Starting from Fall 2023, I am actively seeking motivated undergrad/graduate students for collaboration. If you are passionate about research and eager to work on innovative projects in deep learning, consider joining our research lab and working with me. You will have the opportunity to lead your own research projects or contribute to ongoing studies. To apply for an internship, please fill out this form and directly reach out to me via email :)

Recent Publications

In no particular order, these are works that represent my current research focus.

  • Promoting Exploration in Memory-Augmented Adam using Critical Momenta
  • ArXiv Pre-print
  • [Link]

  • EpiK-Eval: Evaluation for Language Models as Epistemic Models
  • EMNLP 2023
  • [Link]

Other Information

  • When not at my computer, I am usually reading books and cooking (with the occasionally movie watching spree). I also enjoy exercise, mainly cycling, swimming and badminton. Other than that, I like both deep-sea and river fishing. I play with rotund pets occasionally and admire round seals.
  • My research is generously supported by the following organizations.