Speakers
Alessandro Bria, University of Cassino and Lazio Meridionale
Biography: Alessandro Bria received a MSc degree in Computer Engineering from the University of L'Aquila in 2010 and a Ph.D. Degree in Electrical and Information Engineering from the University of Cassino in 2014. In 2019 he joined the Department of Electrical and Information Engineering (DIEI) at the University of Cassino and Southern Lazio, where is now an Associate Professor in Computer Science and Artificial Intelligence. He has authored over 60 International Journals and Conference Proceedings research papers. He is a member of the editorial board of the journals “Frontiers in Artificial Intelligence” and “Frontiers in Big Data”, and of the International Association of Pattern Recognition (IAPR). His current research interests include medical image analysis (breast mammo/DBT, lung CT, brain MRI), EEG signal analysis, and unstructured EHR analysis. He is co-inventor of TeraStitcher and TeraFly for reconstruction and assisted visualization of terabyte-sized microscopy images.
Lecture: Leveraging Transformer Models in Healthcare
The advent of Transformer models and attentional mechanisms has revolutionized the field of artificial intelligence, offering unprecedented capabilities in natural language processing, computer vision, bioinformatics, and multimodal data integration. We will begin with an overview of the fundamental principles underlying attentional mechanisms and Transformer models. The seminar will then highlight key applications in healthcare, such as the analysis of electronic health records (EHRs), medical imaging, and drug discovery. By the end of the seminar, attendees will be equipped with a comprehensive understanding of how Transformer models can drive innovation and improve outcomes in healthcare and biological research.
Concetto Spampinato, University of Catania
Biography: Concetto Spampinato earned his Laurea degree and completed his PhD in Computer Engineering at the University of Catania in 2004 and 2008, respectively. He currently serves as an Associate Professor at the same institution. He spent a research term at the University of Edinburgh during 2008- 2009, concentrating on object detection and recognition. Since October 2016, he has been a Courtesy Faculty member at Center for Research in Computer Vision at the University of Central Florida. Dr. Spampinato’s research focuses on learning-based computer vision and pattern recognition, especially using deep learning techniques. In 2014, he founded the Pattern Recognition and Computer Vision Laboratory at the University of Catania. He has authored over 200 publications and led various EU, national, and regional projects on foundational AI and its applications.
Lecture: Advancing Vision: Models, Tuning, and Generative Breakthroughs
Foundation models have revolutionized computer vision, with Vision Transformers (ViTs) emerging as a cornerstone in understanding and manipulating visual data. This talk explores the evolution and impact of ViTs and other transformative architectures, highlighting their effectiveness in tasks such as image classification, object detection, and semantic segmentation. The discussion extends to foundation generative models, particularly diffusion models, which have fundamentally changed image generation by iteratively refining predictions. We delve into their principles and showcase their applications, emphasizing their role in enhancing creativity and fidelity in visual content creation. Furthermore, the presentation introduces techniques like prompt tuning that enable optimizing foundation models—such as ViTs and others—for specific downstream applications, without extensive re-training. Through these insights, this talk provides the latest advancements in foundation and generative models, underscoring their potential to reshape computer vision paradigms and catalyze new possibilities across diverse fields and applications.
Danilo Comminiello, Sapienza University of Rome
Biography: Danilo Comminiello is an Associate Professor with the Department of Information Engineering, Electronics and Telecommunications (DIET) of Sapienza University of Rome, Italy. His research interests concern the design and analysis of modern artificial intelligence algorithms, including neural networks and machine learning methods, deep generative models, and adaptive learning systems, with application to several fields, from audio to images, from medical to sensor signals. Danilo Comminiello is an IEEE Senior Member. He is an elected member and Vice-Chair of the IEEE Machine Learning for Signal Processing Technical Committee. He is the Chair of the IEEE Task Force on Computational Audio Processing. Danilo Comminiello serves as an Area Editor for IEEE Signal Processing Magazine and as an Associate Editor for IEEE Transactions on Neural Networks and Learning Systems. He is one of the editors of the book Adaptive Learning Methods for Nonlinear System Modeling (D. Comminiello and J. C. Principe, eds.), Elsevier 2018. Danilo Comminiello is the General Chair of the 33rd IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2023), September 17-20, 2023, Rome, Italy, and of the INNS International Joint Conference on Neural Networks (IJCNN 2025), June 30 – July 5, 2025, Rome, Italy.
Lecture: Turning Noise into Discovery: Generative AI in Healthcare and Life Sciences
Generative AI is revolutionizing healthcare and life sciences, ushering in a paradigm shift in how complex problems are addressed. This talk will spotlight the latest generative models, unveiling their sophisticated mechanisms and transformative potential. We will explore a range of groundbreaking applications, from enhancing diagnostic precision and personalizing treatments to accelerating drug discovery and advancing biological research. Attendees will gain valuable insights into the innovative power of generative AI and its profound impact on healthcare and life sciences, charting a course towards more effective and personalized solutions in these critical fields. Generative AI is revolutionizing healthcare and life sciences, resulting in a paradigm shift in how complex problems are addressed. This talk will highlight the latest generative models, showing their sophisticated mechanisms and transformative potential. We will explore a range of groundbreaking applications, from improving diagnostic accuracy and personalizing treatments to accelerating drug discovery and advancing biological research. Participants will gain insights into the revolutionary potential of generative AI and its profound impact on healthcare and life sciences, paving the way towards more effective and personalized solutions in these critical fields.
Enea Parimbelli, University of Pavia
Biography: Enea Parimbelli is assistant professor of biomedical engineering at the Department of Electrical, Computer and Biomedical engineering at the University of Pavia (Italy). Enea’s research revolves around biomedical applications of AI, decision support, health informatics, e- and m-health. Enea thoroughly enjoys scientific research and teaching, interdisciplinary work and cross-pollination between fields, which are the main drivers for his willingness to work in biomedical research. In his free time Enea is also a fish-geek, enjoys beach- and indoor volleyball, good books and weird movies.
Lecture: From the first draft to the manuscript acceptance
Academic publishing, i.e., reading and writing about scientific research, is an integral part of the work of every scientist regardless of the specific career stage. In recent years the landscape has been rapidly changing with the advent, and establishment, of open-science practices, preprints, predatory publications and the never-ending increase in the number of active researchers, submissions and published articles. The lecture aims at giving an introduction to some of the key points that researchers in training need to better navigate this complexity, which will become the cornerstone of the evaluation of the quality of the research they produce, career advancement and establishing credibility in the field. We will touch upon topics such as conducting a proper “related work” literature search, selecting the best publication venues for original work, best practices regarding reporting and reproducibility, and other relevant themes. Suggestions for specific research-oriented tools will also be provided during class, to facilitate immediate transfer of best practices into researchers’ workflow.
Fabrizio Silvestri, Sapienza University of Rome
Biography: Fabrizio Silvestri is a Full Professor at the Department of Computer, Control and Management Engineering at Sapienza University of Rome. His research interests focus on Artificial Intelligence, particularly machine learning applied to web search problems and natural language processing. He has authored more than 150 papers in international journals and conference proceedings and holds nine industrial patents. Silvestri has been recognized with a "test-of-time'' award at the ECIR 2018 conference for an article published in 2007. He also received three best paper awards and other international recognitions. Silvestri spent eight years in industrial research laboratories, including Yahoo! and Facebook. At Facebook AI, he directed research groups to develop artificial intelligence techniques to combat malicious actors who use the Facebook platform for malicious purposes, such as hate speech, misinformation, and terrorism. Silvestri has experience in organizing numerous workshops and conferences, and he will be one of the General Chairs of ECIR 2025 in Lucca and one of the Program Committee Chairs of CIKM 2026 in Rome. Silvestri holds a Ph.D. in computer science from the University of Pisa, with a thesis on "High-Performance Issues in Web Search Engines: Algorithms and Techniques''.
Lecture: Unlocking Medical Knowledge: Large Language Models and Retrieval Augmented Generation
This lecture will explore the potential of Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) to revolutionise healthcare. We'll start by looking at the core concepts of LLMs, exploring their capabilities and limitations in understanding and processing vast amounts of natural language data. Next, we will introduce Retrieval Augmented Generation (RAG), a transformative approach that enables LLMs to retrieve more accurate and relevant information from databases. This integration improves the accuracy and informativeness of LLM outputs, making them valuable assets for a variety of tasks. Throughout the presentation, we will explore recent advances in LLM and RAG applications in healthcare. We will discuss how such advancements can transform healthcare workflows, improve patient care, and open new avenues for medical research.
Federico Cabitza, University of Milan-Bicocca
Biography: Federico Cabitza is an associate professor at the University of Milano-Bicocca (Milan, Italy) where he teaches human-computer interaction, information systems and decision support. He is head of the Laboratory of Uncertainty Models, Decisions and Interactions in the department of Informatics at the above-mentioned university and is director of the local node of the national laboratory "Computer Science and Society." Since 2016, he has been collaborating with several hospitals, including the IRCCS Galeazzi Orthopaedic Institute in Milan, Italy, with which he has a formal affiliation and founded the Medical Artificial Intelligence Laboratory. He is associate editor of the International Journal of Medical Informatics (Elsevier ISSN: 1386-5056) and a member of several editorial boards, including Mondo Digitale, the official AICA journal. His research interests are in the design and evaluation of artificial intelligence systems to support decision making, especially in health care and law, and the impact of these technologies on the organizations that adopt them. To date, he has published more than 160 research publications in international conference proceedings, edited books and high-impact scientific journals and is listed among the world's most influential scientists, according to Stanford's Top 2% Scientists list. He is the author with Luciano Floridi of the book "Artificial Intelligence, the use of new machines" published by Bompiani.
Lecture: Evidence-Based eXplainable AI - how to ground our AI interventions on empirical research
What does it mean to take an evidence-based approach to the design and evaluation of decision support interventions that employ explainable AI systems? In this talk we will look at an EBXAI framework that includes an evidence strength scale, to motivate studies that employ real-world (yet vetted) datasets and involve real practitioners, a set of design-oriented concepts and model- and performance-oriented metrics (namely data reliability, model utility, model calibration, model robustness and model impact on decision making) that can be used to compare and evaluate XAI solutions, which we have implemented in an online tool made freely accessible to the serious practitioner in AI and ML-enabled Decision Support.
Giorgia Carra, Lausanne University Hospital
Biography: Dr. Carra is a Senior Data Scientist at the Biomedical Data Science Center of the University Hospital of Lausanne, in Switzerland. Her research is centered on the development and clinical translation of AI-driven algorithms, with a particular focus on infectious diseases and sepsis. Additionally, she has a keen interest in clinical AI regulatory compliance and technology validation through collection of real-world evidence.
Lecture: Making Healthcare Smarter: Clinical AI for Decision Support and Process Optimization
Artificial Intelligence (AI) is revolutionizing healthcare, with increasing expectations for using AI-based algorithms to deliver more personalized and cost-effective care. As such, AI is becoming one of the most promising and rapidly evolving fields in modern medicine. In this presentation, we will discuss state-of-the-art research trends, potential applications, the challenges, and the benefits of using AI in healthcare. After a general overview, we will delve into the efforts of CHUV (Centre Hospitalier Universitaire Vaudois) in Switzerland to develop and implement various AI-driven tools at the bedside to assist healthcare professionals in diagnosing diseases, predicting patient complications, and optimizing healthcare operations. Furthermore, we will address the technical, ethical, and regulatory challenges of implementing AI in healthcare, and analyze some successful examples. This presentation aims to provide a comprehensive overview of the benefits and challenges of clinical AI development and implementation.
Merixtell Bach Cuadra, University of Lausanne
Biography:
Lecture:
TBD
Pierre Baldi, University of California
Biography: Pierre Baldi grew up in Rome and earned MS degrees in Mathematics and Psychology from the University of Paris, and a PhD in Mathematics from the California Institute of Technology. He is currently Distinguished Professor in the Department of Computer Science, Director of the Institute for Genomics and Bioinformatics, and Associate Director of the Center for Machine Learning and Intelligent Systems at the University of California Irvine. The long term focus of his research is on understanding intelligence in brains and machines. He has made several contributions to the theory of AI and deep learning, and developed and applied AI and deep learning methods for the natural sciences, to address problems in physics (e.g., exotic particle detection) , chemistry (e.g., reaction prediction), and bio-medicine (e.g., protein structure prediction, biomedical imaging analysis), circadian rhythms. He recently published his fifth book: Deep Learning in Science, Cambridge University Press (2021). His honors include the 1993 Lew Allen Award at JPL, the 2010 E. R. Caianiello Prize for research in machine learning, the 2023 Dennis Gabor Award, and election to Fellow of the AAAS, AAAI, IEEE, ACM, and ISCB. He has co-founded several startup companies.
Lecture: The AI-driven Hospital of the Future
AI today can pass the Turing test and is in the process of transforming science, technology, society, humans, and beyond. Surprisingly modern AI is built out of two very simple and old ideas, rebranded as deep learning: neural networks and gradient descent learning. I will describe several applications of AI to problems in biomedicine developed in my laboratory, from the molecular level to the patient level using omic data, imaging data, clinical data, and beyond. I will discuss the opportunities and challenges for developing, integrating, and deploying AI in the first AI-driven hospitals of the future and present two frameworks for addressing some of the most pressing societal issues related to AI research.