Massimiliano Mancini is a researcher in the Explainable Machine Learning grou, and a Ph.D. student in Engineering in Computer Science at Sapienza University of Rome, supervised by Prof. Barbara Caputo and Prof. Elisa. He is also a member of the ELLIS Ph.D. program, advised by Prof. Zeynep Akata. He received his master's degree in Artificial Intelligence and Robotics with honors from the Sapienza University of Rome in 2016 and his bachelor's degree in Computer Science and Electronic Engineering from the University of Perugia in 2014. During his Ph.D. he has been a member of the Technologies of Vision lab at Fondazione Bruno Kessler and of the Visual Learning and Multimodal Applications Laboratory of the Italian Institute of Technology. During summer 2018, he was a visiting Ph.D. student in the Robotics, Perception and Learning Laboratory at KTH Royal Institute of Technology in Stockholm.





Massimiliano Mancini's research interest is mainly in breaking the closed-world assumption of pretrained models, whose knowledge is inherently limited to the particular training set they are trained on. In particular, his focus is mostly in scenarios where the input distribution is changing at test time (such as domain adaptation/generalization) and/or the new semantic concepts are added over time (such as incremental/multi-domain learning, open-world recognition, and zero-shot learning).