M Saiful Bari (Maruf) is the Training Lead and one of the Core Maintainers of ALLaM, a sovereign foundational model for English and Arabic language technologies. His research focuses on understanding and advancing large language models, particularly in the areas of scaling, training dynamics, and systematic evaluation of frontier (-> superintelligence) models. His lab investigates these aspects through three primary areas: (1) scaling behaviors and training dynamics of large language models in terms of data and truthfulness, (2) developing robust evaluation methodologies for frontier class (-> superintelligence) models with scalable-oversight, and (3) exploring efficient learning paradigms through transfer learning at scale. This research combines theoretical frameworks with large-scale empirical studies, leading to both methodological innovations and practical applications.

Maruf received his Ph.D. from Nanyang Technological University under the supervision of Prof. Shafiq Joty, where his thesis explored transfer learning for large language model adaptation, addressing the fundamental question: How can you learn so much from so little?. During his doctoral studies, he attended three internships at Amazon Web Services (2021-2023) and made substantial contributions to the BLOOM LLM development, particularly in its architecture design, pretraining, and prompt engineering efforts.