Curriculum vitae.
Machine learning research with foundations in mathematics and experience across applied domains.
Education
PhD in Computer Science
Université de Montréal · Mila
Supervised by Ioannis Mitliagkas and Aristide Baratin.
MSc in Computer Science
McGill University · Mila
Supervised by David Rolnick. Research on neural network geometry and interpretability.
BSc in Computer Science
Sharif University of Technology
Minor in Mathematics (2019–2022).
Experience
Research Intern
McGill University
Worked on biological causality and variational likelihood-free inference using genotype and phenotype data.
Machine Learning Scientist
AIMed
Worked on deep learning for medical imaging, including CT-based analysis of COVID-19 and lung disease.
Machine Learning Engineer
FANAP
Worked on automatic speech recognition with convolutional models for temporal features.
Recognition
Inter-Math-AI Scholarship, 2024
Selected publications
Navigating Potholes with Geometry-Aware Sharpness Minimization
Simon Dufort-Labbé, Mehrab Hamidi, Razvan Pascanu, Ioannis Mitliagkas, Damien Scieur, Aristide Baratin
arXiv preprint · 2026
T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
Alireza Dizaji, Benedict Aaron Tjandra, Mehrab Hamidi, Shenyang Huang, Guillaume Rabusseau
ACM SIGKDD 2026 · 2026
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
Karolis Jucys, George Adamopoulos, Mehrab Hamidi, Stephanie Milani, Mohammad Reza Samsami, Artem Zholus, Sonia Joseph, Blake Richards, Irina Rish, Özgür Şimşek
Mechanistic Interpretability Workshop at ICML 2024 · 2024