Organizers

	Jun.-Prof. Dr. Gesina Schwalbe Ulm University	Gesina Schwalbe is assistant professor at Ulm University since Apr 2026, and since Sep 2024 leads her own junior research group Correctable Hybrid AI. The group investigates how concept-based explainability can be used for model verification and correction of computer vision DNNs. This builds upon her general research of safety assurance and trustworthiness of AI using XAI techniques, which she pursued throughout her PhD (2018–2022, University of Bamberg) and postdoctoral phases at Continental AG (until 2023) and the Hybrid AI lab at University of Lübeck (2024–2026). She received her masters degree in mathematics at the University of Regensburg. Currently she lectures the course Explainable Artificial Intelligence at Ulm University, and in the past several courses on foundations of machine learning.
	Dr. Jae Hee Lee University of Hamburg	Jae Hee Lee is a principal investigator at the University of Hamburg, where he co-leads the DFG-funded projects LUMO and E4-MALM. His research focuses on developing trustworthy AI systems that can reason robustly across language, vision, and action while making their internal representations and decisions more interpretable. His work lies at the intersection of multimodal learning, explainable AI, neuro-symbolic AI, continual learning, and mechanistic interpretability. In LUMO, he investigates how concept-based explanations and compositional knowledge can improve robust lifelong multimodal learning. In E4-MALM, he studies the evaluation and mechanistic explanation of ethical behavior and collective failure modes in multi-agent systems of large language models. Before joining the University of Hamburg, he held postdoctoral positions at Cardiff University, the University of Technology Sydney, and the Australian National University. He received his PhD and Diplom degree from the University of Bremen.
	M. Mahdi Pourghasem University of Lübeck	M. Mahdi Pourghasem is a PhD student at the University of Lübeck, where he has been working since July 2025. He is a member of the Junior Research Group Correctable Hybrid Artificial Intelligence (chAI), led by Jun.-Prof. Gesina Schwalbe. His research interests lie in neuro-symbolic AI, with a focus on developing artificial intelligence systems that combine deep learning with symbolic reasoning. He is especially interested in learning structured relational and knowledge representations under weak or sparse supervision. More broadly, his work investigates how symbolic reasoning can guide neural representation learning and improve the reliability, interpretability, and formal guarantees of AI systems. He is particularly interested in rule injection methods, such as using symbolic constraints as semantic losses during learning.