Keynote Speakers
Foundation models for health signals
The unprecedented success of foundation models has transformed our understanding of artificial intelligence, yet their application to personal health and ubiquitous sensing remains a complex frontier. In this talk, I will share my journey in building AI for health monitoring, starting with early efforts to improve data efficiency, robustness, and fairness through self-supervision. A key milestone in this journey was the development of PaPaGei, the first open foundation model for photoplethysmography (PPG). While PaPaGei demonstrated the utility of pre-training on various biosignal datasets, the rigorous demands of real-world applications, such as accurate activity recognition, heart rate, or other biomarker monitoring in dynamic environments, highlight the need for even greater generalization and scale. These challenges motivate the transition to Large Sensor Models that address these hurdles by scaling up both model size and the diversity of user data. This scaling unlocks emergent benefits that smaller models cannot achieve, positioning such foundation models to become the backbone of any future sensing task.
Biography
Dimitris Spathis is a research scientist at Google and a visiting researcher at the University of Cambridge. His work enables AI to handle the messiness of the real world through data-efficient and robust machine learning, with a focus on building foundation models for health. He is particularly interested in the following areas:
AI for Sequential & Multimodal Data: Developing and releasing AI models that make the most of fine-grained person-generated data through self-supervised learning [ICLR'25, CHIL'21], multimodal fusion [WSDM'24], forecasting [KDD'19 oral], and knowledge distillation [UbiComp'21].
Accessible Health Sensing: Building AI systems that detect vital health information without specialized equipment, with applications to disease monitoring [NeurIPS'21], cardio fitness [Nature Dig. Medicine'22], sleep disorders [Sci. Reports'22], and more.
Robust & Trustworthy AI: Development of reliable ML algorithms for high-stakes applications, focusing on out-of-distribution generalization [ML4H'22, ACLw'17], addressing forgetting [WACV'24], fairness [KDD'24], and ethical considerations [JAMIA'21].
Previously, he was a senior research scientist at Nokia Bell Labs, leading efforts in AI for multimodal health. Before that, he completed a PhD in Computer Science at the University of Cambridge, working with Prof. Cecilia Mascolo. During his studies, he worked at Microsoft Research, Telefonica Research, and Ocado. He also helped start COVID-19 Sounds, one of the largest studies in audio AI for health.His research has been published in top venues in artificial intelligence, AI for health, and human-centered signal processing while recent projects have been featured in international media such as the New York Times, BBC, CNN, Guardian, Washington Post, Forbes, and Financial Times.
Interview Simulation Workshop
Biography
Nikolaos Korfiatis is a Professor in the Department of Informatics at the Ionian University, specializing in Data Management. He received his undergraduate degree from the Athens University of Economics and Business (2004), continued with postgraduate studies (MEng) at the Royal Institute of Technology (KTH) in Stockholm, Sweden, and obtained a PhD from Copenhagen Business School (2009). He then worked as Assistant Professor in Experimental and Behavioral Economics at the Department of Economics, University of Copenhagen (Denmark), and as Lecturer (2009–2014) in Information Systems and Databases at Goethe University Frankfurt (Federal Republic of Germany). Subsequently, he served as Assistant, Associate, and Full Professor at the University of East Anglia (UEA), Warwick Business School, and the University of Nottingham, where he retired and later joined the faculty of the Department of Informatics at the Ionian University.
Presentation of Research Laboratory CMODLab
Biography
Dr. Ioannis Karydis holds a BEng in
Engineering Science & Technology from Brunel University, UK (2000),
an MSc in Advanced Methods in Computer Science from Queen Mary
University, UK (2001) and a PhD in Computer Science from the dept. of
Informatics of Aristotle University of Thessaloniki, Greece (2006).
Research Interests
- Musical genre classification
- Voice separation in polyphonic music
- Continuous querying in musical streams
- New media cultural informational systems
- Music information retrieval user interface design
- Musical data similarity using contextual information
- Musical data management in p2p networks
- Internet of Multimedia Things (M-IoT / IoMT)
- New media co-creational systems
- Collective intelligence in new media
EVANGELIA ZOI AKRITIDI
Ionian UniversityDigital Transformation and Academic Tech Startups: How IT Tools Support Innovation and Sustainability
The proposed presentation examines the role of digital transformation and IT tools in fostering innovation and sustainability among academic tech startups. It focuses on the key challenges faced by university initiatives, such as uncertainty, the commercialization of research knowledge, and market engagement, and highlights the role of information systems, data analysis, artificial intelligence, and digital twins as support mechanisms. At the same time, it underscores the importance of the topic for computer science students and young researchers, within the context of academic specialization and innovative university initiatives.