Published several papers including 'Learning Multi-Agent Communication with Contrastive Learning' (ICLR 2024), 'Language Model Alignment with Elastic Reset' (NeurIPS 2023), and more, with some works having their code publicly available.
Research Experience
Has been involved as a researcher in multiple projects focusing on areas such as multi-agent communication, language model alignment, self-supervised learning, etc.
Education
Graduated from the University of Waterloo with a Bachelor's in Software Engineering in 2017; Completed his Master's at Université de Montréal in 2019; Now a PhD student at Mila, supervised by Aaron Courville.
Background
Research interests include interacting with humans through language, NLP, and reinforcement learning. Currently a PhD candidate in AI at Mila, associated with Université de Montréal.
Miscellany
Spoke about some of his research interests on a podcast.