Skip to content
← Back to Team
Integrated Researchers

Maryam Abbasi

FCT TENURE Computer Science

Universidade Politécnica de Santarém · Iran

Computer Sciences

Profile

About

Maryam Abbasi is a researcher in Artificial Intelligence and Machine Learning, with a PhD in Informatics Engineering from the University of Coimbra (2019, Distinction and Honour). She holds a full research-career contract as Auxiliary Researcher at CIAC-PLDIS (Pólo de Literacia Digital e Inclusão Social of the Centre for Research in Arts and Communication) at the Polytechnic Institute of Santarém, where she also teaches Artificial Intelligence courses at the School of Management and Technology. She is a collaborating researcher at the Laboratory of Artificial Neural Networks (LARN), CISUC, University of Coimbra.

Her research sits between Artificial Intelligence, Bioinformatics, Health and Behavioural Sciences, with a focus on deep generative models, multi-objective reinforcement learning, transformer architectures, explainable AI (XAI), and the combination of knowledge graphs with large language models. She has led and taken part in competitive projects funded by FCT, Horizon Europe, MIT Portugal and PRIMA, with applications in education, drug discovery, antimicrobial peptide design, precision oncology and sustainable agriculture.

She has co-supervised two completed PhDs, both awarded with distinction, along with several master's and undergraduate students. She contributes to advanced training, science communication and international scientific dissemination, including keynote lectures, invited webinars and program committee memberships at international conferences. Her work has resulted in over 100 publications, including papers in leading Q1 journals such as Briefings in Bioinformatics, Journal of Cheminformatics, Artificial Intelligence in Medicine and Computers in Biology and Medicine.

Research

Research interests

Deep learning; explainable artificial intelligence; multi-objective reinforcement learning; applied artificial intelligence in education and biological problems; knowledge graphs and large language models (LLMs).