Lukas Kuhn is a Research Scientist working on predictive multimodal learning, world models, and clinical AI. His research focuses on learning structured latent representations from images, language, and other heterogeneous data sources, with the goal of enabling robust prediction, temporal modeling, and decision-making. More broadly, he is interested in self-supervised and non-contrastive learning, multimodal foundation models, and the development of reliable AI systems for high-impact real-world applications.