Michael Rizvi-Martel
Hey I'm Michael!
Click here for fun animal facts
About me
Welcome to my page!
My name is Michael and I am a PhD student in Computer Science at Mila and Université de Montréal.
I am supervised by both prof. Guillaume Rabusseau and prof. Adam Oberman.
My research interests are all over the place, but I am generally interested leveraging tools from formal language theory and theoretical computer science
to better understand the performance and limitations of language models. I believe that such tools create a great framework for better understanding
the intersection between learning and “reasoning” tasks (through the lense of algorithmic reasoning).
I am also interested in the application of neurosymbolic AI to problems in pure maths, such as proof synthesis and am
tangentially interested in questions concerning identifiability and representation learning (more recently the disentangled variety).
Overall, my goal is to better understand the limitations of modern AI when it comes to complex reasoning tasks and (hopefully!)
design future AI systems which overcome such limitations.
When I am not publishing or perishing, you can find me rock climbing, hiking or canoe camping!
I am also an avid guitar player and love discovering new (and old) restaurants in the Montréal area :)
News
- Our paper with Maude Lizaire was chosen for an ICML spotlight!
Publications
- Lizaire, M., Rizvi-Martel, M., Gamal, M., & Rabusseau, G. A Tensor Decomposition Perspective on Second-order RNNs. In Forty-first International Conference on Machine Learning. (Spotlight!)
- Rizvi-Martel M., Lizaire, M., Lacroce, C., & Rabusseau, G. (2024, April). Simulating weighted automata over sequences and trees with transformers. In International Conference on Artificial Intelligence and Statistics (pp. 2368-2376). PMLR.
Talks
CV
Download my CV here.
Socials
