Scholar
Sékou-Oumar Kaba
Google Scholar ID: jKqh8jAAAAAJ
McGill University & Mila - Quebec Artificial Intelligence Institute
Citations & Impact
Citations
694
H-index
9
i10-index
9
Publications
17
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Published several conference papers such as 'Energy Loss Function for Physical Systems' (NeurIPS 2025), 'Improving Equivariant Networks with Probabilistic Symmetry Breaking' (ICLR 2025); journal articles like 'Prediction of Large Magnetic Moment Materials with Graph Neural Networks and Random Forests' (Phys. Rev. Materials, 2023); preprints such as 'Accurate and Scalable Exchange-Correlation with Deep Learning' (2025).
Research Experience
- Works on geometric deep learning and generative modeling for molecules, crystals, and materials at McGill and Mila. Interned at Microsoft Research Amsterdam working on machine learning for electronic structure.
Education
- Ph.D. candidate in Computer Science at McGill University, supervised by Prof. Siamak Ravanbakhsh; interned at Microsoft Research Amsterdam working on machine learning for electronic structure; completed an M.Sc. in theoretical condensed matter physics with Prof. David Sénéchal and interned in Prof. Yoshua Bengio's group at Mila before starting the Ph.D.
Background
- Research interests include geometric deep learning, ML models for scientific discovery, particularly symmetry, equivariance, and AI for materials and molecular systems. Also interested in graph learning and statistical physics.
Miscellany
- Cares deeply about science outreach and communication, hosted a radio show on scientific and social innovation, and continues to seek opportunities to make scientific ideas accessible and inspiring to a broader audience.
