Machine learning researcher / Montréal, Canada

Mehrab Hamidi.

Understanding how neural networks learn, reason, and generalize.

I'm a PhD student at Université de Montréal and a researcher at Mila. I work at the intersection of deep learning theory, optimization, and mechanistic interpretability.

Supervised by Ioannis Mitliagkas and Aristide Baratin.

Mehrab Hamidi
PhD student · Université de MontréalResearcher · Mila, Quebec AI Institute
Research & education Mila – Quebec AI Institute Université de Montréal McGill University Sharif University of Technology emblemSharif University
of Technology
Research directions

Making learning systems
more understandable.

I connect theoretical questions about neural networks with experiments that reveal how models behave.

01 /

Geometry & optimization

Studying the structure of neural representations and loss landscapes to understand learning dynamics and improve optimization.

Deep learning theoryOptimization
02 /

Mechanistic interpretability

Connecting a model's internal computations to its behavior, with a focus on vision-based agents and sequential decisions.

InterpretabilityAgent behavior
03 /

Temporal reasoning

Designing controlled benchmarks that reveal how graph models handle memory, delayed effects, and long-range dependencies.

Graph learningEvaluation
Selected work

Research, in practice.

All publications
Recent updates

News & milestones.

All news ↗
Research

A Floquet view of recurrent memory

A research note explains what periodic dynamics can reveal about memory, alongside graph prediction failures, incomplete contraction evidence, and a bit retained through 6,144 steps.

Publication

T-GRAB at KDD 2026

T-GRAB is published in the ACM SIGKDD proceedings, introducing diagnostic tasks for temporal graph learning.

From the notebook

Ideas worth unpacking.

Visit the blog ↗
A little background

From theory
to applications.

Before my PhD, I completed an MSc at McGill with David Rolnick and a BSc in Computer Science with a mathematics minor at Sharif University of Technology.

My earlier work spans medical imaging, statistical inference in biology, and speech recognition.

Experience & education ↗
Beyond the research

Outside research, I enjoy hiking, tennis, and making music. I play the violin, kamancheh, and saxophone.

Mehrab
Let's connect

Good research starts
with a conversation.

Interested in research scientist and research engineer opportunities, and collaborations on understanding and improving learning systems.

mehrab.hamidi@mila.quebec