Semih Cantürk

I’m a PhD candidate at Mila – Quebec AI Institute and Université de Montréal DIRO, in Guy Wolf’s group. My interests cover theory and applications of geometric and topological deep learning, with a focus on graph representation learning (GRL) and spectral graph theory. I am particularly interested in solving combinatorial optimization problems with GRL, leveraging geometric learning tools on biomolecular data, and developing effective positional and structural encodings (PSE) for more effective and scalable graph learning.

I completed my MSc also at Mila & UdeM, and previously obtained my BEng from the University of Pennsylvania (Penn). Recently, I was a visiting researcher at Christopher Morris’s LOG Group @ RWTH Aachen in Fall 2025. I was also a PhD Intern at Valence Labs in 2024, working on accelerating molecular dynamics simulations via MLIPs.

Previously, I was as an ML Engineer at Zetane Systems. My other work experience include internships and research stints at the Imperial College Data Science Institute (distributed computing), SAS Analytics (data science) and InfoTRON (AR/VR).