Souhaib Ben Taieb is an Associate Professor at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) in Abu Dhabi, United Arab Emirates. His research spans artificial intelligence and statistics, including probabilistic machine learning, uncertainty quantification, model calibration, scoring rules, time series forecasting, and anomaly detection.
Previously, he was an Associate Professor of Machine Learning at the University of Mons (UMONS) in Belgium. Prior to that, he served as a Lecturer (Assistant Professor) in Business Analytics in the Department of Econometrics and Business Statistics at Monash University in Melbourne, Australia. He was also a postdoctoral research fellow in the Spatio-Temporal Statistics and Data Science group at KAUST in Saudi Arabia. Souhaib holds a Ph.D. in Computer Science (Machine Learning) from the Free University of Brussels (ULB), where he also earned his B.Sc. and M.Sc. in Computer Science.
He has secured competitive research funding from both academic institutions and industrial partners, including collaborations with Huawei, John Cockerill, and Ion Beam Applications. He received a Doctoral Research Fellowship from the Belgian National Fund for Scientific Research (FNRS) and was awarded the Solvay Award for the best Ph.D. thesis. He currently serves as an Associate Editor for the International Journal of Forecasting and regularly reviews for leading conferences and journals in machine learning and statistics.
Recent publications
- Thao Nguyen, Jiaqi Ma, Fahad Shahbaz Khan, Souhaib Ben Taieb, Salman Khan (2026) RainDiff, End-to-end Precipitation Nowcasting Via Token-wise Attention Diffusion. Abstract Arxiv
- Naomi Desobry, Elnura Zhalieva, Souhaib Ben Taieb (2026) Enforcing Calibration in Multi-Output Probabilistic Regression with Pre-rank Regularization. Abstract Arxiv
- M. Stocker, W. MaĆgorzewicz, M. Fontana, Souhaib Ben Taieb (2026) A Gentle Introduction to Conformal Time Series Forecasting. Abstract Arxiv
- Nabil Alami, Jad Zakharia, Souhaib Ben Taieb (2025) Symmetric Aggregation of Conformity Scores for Efficient Uncertainty Sets. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Press, 2026.. Abstract Arxiv
- Victor Dheur, Souhaib Ben Taieb (2025) Multivariate Latent Recalibration for Conditional Normalizing Flows. Neural Information Processing Systems (NEURIPS), 2025.. Abstract Arxiv