Eleonora Poeta

Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 39^th cycle (2023-2026)
Department of Control and Computer Engineering (DAUIN)

Docente esterno e/o collaboratore didattico
Department of Control and Computer Engineering (DAUIN)

eleonora.poeta@polito.it

Profile

PhD

Research topic

Safe and Trustworthy AI

Tutors

Research interests

Data science, Computer vision and AI

Biography

I obtained my Master's degree in Data Science and Engineering from the Politecnico di Torino in April 2023. I am currently in the second year of the PhD program in Computer and Control Engineering (39th cycle) at the same university, where I am part of the Database and Data Mining Group (DBDMG) within the DAUIN department.
My research focuses on analyzing and developing methods for Safe and Trustworthy AI, with an emphasis on robustness, interpretability, and explainability. I am exploring concept-based explainable AI (C-XAI) techniques to improve the transparency and reliability of AI models, as well as investigating methodologies to evaluate the robustness of models in sensitive domains, such as medical AI.

Awards and Honors

Best Paper Award MAMA-MIA Challenge at MICCAI 2025 (2025)

Teaching

Teachings

Master of Science

Explainable and trustworthy AI. A.A. 2024/25, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
Business intelligence per big data. A.A. 2024/25, INGEGNERIA GESTIONALE. Collaboratore del corso
Data science lab: process and methods. A.A. 2024/25, DATA SCIENCE AND ENGINEERING. Collaboratore del corso
Explainable and trustworthy AI. A.A. 2023/24, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
Business intelligence per big data. A.A. 2023/24, INGEGNERIA GESTIONALE. Collaboratore del corso

MostraNascondi A.A. passati

Research

Research groups

DBDM - Database and Data Mining Group (DAUIN)

Publications

Latest publications View all publications in Porto@Iris

Vargas, Luisa; Poeta, Eleonora; Cerquitelli, Tania; Baralis, Elena; Zuluaga, Maria A. (In stampa)
MedOpenSeg: Open-World Medical Segmentation with Memory-Augmented Transformers. In: 36th British Machine Vision Conference, Sheffield (UK), 24th - 27th November 2025
Contributo in Atti di Convegno (Proceeding)
Rege Cambrin, Daniele; Poeta, Eleonora; Pastor, Eliana; Corley, Isaac; Cerquitelli, ... (In stampa)
HydroChronos: Forecasting Decades of Surface Water Change. In: International Conference on Advances in Geographic Information Systems 2025, Minneapolis (USA), November 3 - 6, 2025
Contributo in Atti di Convegno (Proceeding)
Septiers, Valentin; Sosa-Marrero, Carlos; Poeta, Eleonora; Chourak, Hilda; Briens, ... (2026)
Explainable Prediction of Recurrence After Prostate Cancer Radiotherapy Using in Silico digital twin model and machine learning. In: Digital Twin for Healthcare. DT4H 2025 held in Conjunction with MICCAI 2025 (28th International Conference on Medical Image Computing and Computer Assisted Intervention), Daejeon (KOR), September 23, 2025, pp. 152-163. ISSN 1611-3349. ISBN: 978-3-032-07694-6
Contributo in Atti di Convegno (Proceeding)
Poeta, Eleonora; Vargas, Luisa; Falcetta, Daniele; Marciano', Vincenzo; Pastor, Eliana; ... (2026)
Divergence-Aware Training with Automatic Subgroup Mitigation for Breast Tumor Segmentation. In: Second Deep Breast Workshop, Deep-Breath 2025, Held in Conjunction with MICCAI 2025 (28th International Conference on Medical Image Computing and Computer Assisted Intervention), Daejeon (KOR), September 23rd -27th, 2025, pp. 52-62. ISSN 1611-3349. ISBN: 978-3-032-05559-0
Contributo in Atti di Convegno (Proceeding)
Pastor, Eliana; Poeta, Eleonora; Panisson, André; Perotti, Alan; Ciravegna, Gabriele (2025)
Beyond Input Attribution: A Hands-On Tutorial to Concept-Based Explainable AI and Mechanistic Interpretability. In: 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Toronto ON (CAN), August 3 - 7, 2025, pp. 6247-6248. ISBN: 979-8-4007-1454-2
Contributo in Atti di Convegno (Proceeding)