AI-Powered Report Generation Directly from Surgical Videos. MoReEye aims to reduce the burden on hospital staff by automating surgical report generation and preventing errors. This is based on the automatic analysis of routinely recorded surgical videos. Relevant information is extracted from these videos and then converted into a coherent draft report using a text-generation component. Surgeons always retain control.

aims to advance the translation technologies for German Sign Language (DGS) and French Sign Language (LSF) by overcoming current limitations such as reliance on scarce gloss-annotated data, poor generalization, and unnatural translations.

The MARSS research project (Multimodal System for Combating Disinformation through the Reflection of Socio-Emotional Processes for Students) investigates how AI-based technologies can help students identify, critically reflect on, and combat disinformation and emotional manipulation in digital media.

The CLIKK research project (Chinese language teaching with large language models and a focus on intercultural communication skills) started place in October 2025. It investigates how AI-based virtual agents can support the acquisition of intercultural skills in Chinese language teaching.

is developing an interactive system that uses AI, sensors, and social-interactive agents to generate personalized content to help children ages eight to twelve boost their self-esteem and reduce bullying.

builds the foundation for GDPR-compliant use of health data across the Health.AI alliance: a Trusted Research Environment (TRE) for storing, processing and sharing highly sensitive medical data, plus a data governance strategy for availability, portability and interoperability. Development follows security-by-design and is validated with data from parallel alliance projects. DFKI contributes its SEMLA platform and leads the work on the TRE and the TOM compendium.

addresses obesity in children and adolescents, is developing a digital therapy and diagnostic app, which targets emotional dysregulation, uses a social-digital AI assistance system to provide early, low-threshold access to evidence-based strategies derived from the START program. The goal is to promote emotional resilience and healthy habits in a wide range of young people, ultimately seeking approval for insurance reimbursement.

The NEARBY project aims to develop variability-free BCI systems for use outside the laboratory. To this end, a comprehensive database will be created in which EEG data from various test subjects is recorded over longer periods of time under different conditions and in different environments.The aim is to better understand the variability of the data under different conditions and to develop new algorithms that can reduce or even completely suppress this variability.