Researchers at MBZUAI introduce FissionFusion, a hierarchical model merging approach to improve medical image analysis performance. The method uses local and global aggregation of models based on hyperparameter configurations, along with a cyclical learning rate scheduler for efficient model generation. Experiments show FissionFusion outperforms standard model souping by approximately 6% on HAM10000 and CheXpert datasets and improves OOD performance.
MBZUAI President Eric Xing delivered a talk at Carnegie Mellon University on May 13, 2022, titled “From Learning, to Meta-Learning, to Lego-Learning — theory, systems, and engineering.” Xing discussed the development of a standard model for learning, inspired by the standard model in physics, which aims to unify various machine learning paradigms. Before joining MBZUAI, Xing was a professor at CMU and founder of Petuum Inc., an AI development platform company. Why it matters: This talk highlights MBZUAI's leadership in advancing theoretical frameworks for machine learning and its commitment to unifying different AI approaches.
John Ellis, a theoretical physicist from King's College London, spoke at KAUST's 2019 Winter Enrichment Program about understanding how the universe works. He discussed the Standard Model of particle physics, highlighting fundamental particles and forces. He emphasized the crucial role of the Higgs boson in enabling the formation of atoms and the possibility of life. Why it matters: Understanding fundamental physics is crucial for technological advancement and provides a deeper understanding of our place in the cosmos, inspiring future generations of scientists in the region.