About me
I am a PhD Candidate at Mila-Quebec AI Institute and Université Laval (IID/LSVN lab), and a Visiting Student Researcher at the Stanford Artificial Intelligence Lab. I work in the area of Adversarial Machine Learning under the supervision of Prof. Christian Gagné (Mila & Université Laval) and co-supervised by Prof. Frédéric Precioso (INRIA & Université Côte d’Azur), in close collaboration with Yann Pequignot. At Stanford I am hosted by the Stanford Trustworthy AI Research group (STAIR), led by Prof. Sanmi Koyejo. I was previously a Google AI resident at the Accra Lab, where I was mentored by Yann Dauphin.
Research Interests
My research aims to build safe, efficient and trustworthy machine learning systems that are reliable when deployed in the real world. In particular, I work on:
- Robustness & Safety: adversarial robustness, robust fine-tuning, robustness to distribution shifts, and the safety and alignment of foundation models (LLMs/VLMs)
- Uncertainty & Data Efficiency: uncertainty estimation, test-time scaling and adaptation, and active learning
- Science of Deep Learning: understanding training dynamics and generalization, including grokking and emergent behaviours
Highlights/News
Our work Robust Fine-Tuning with Epsilon-Scheduling is accepted at ICLR 2026!
Excited to join Stanford University this Fall 2025 as a Visiting Student Researcher at the STAIR Lab led by Prof. Sanmi Koyejo!
Attending DLRL 2025, the Deep Learning & Reinforcement Learning Summer School in Edmonton!
Panelist for the 8th Annual Black in AI Workshop at NeurIPS around the theme “AI Regulation & Fairness in the Generative AI Era.”
Winner of the Neptune.ai NeurIPS 2024 Paper Communication Challenge, explaining Margin Consistency at three levels — from 1st grader to researcher: video.
Won a best poster award at the “1ère Journée scientifique de l’IID”!
Our paper on “Margin Consistency” is accepted at NeurIPS 2024! (Twitter thread)
Featured as AIMS Alumni of the Week — read the piece.
In the acknowledgments of the book “Mathematics for Machine Learning” by Prof. Marc Deisenroth — book website.
