Marcus Rohrbach

Marcus Rohrbach is a Full Professor at Technische Universität Darmstadt, leading the 'Multimodal Reliable AI' lab. Previously, he served as a Research Scientist at Meta AI (2017-2023), PostDoc at UC Berkeley (2014-2017), and completed his PhD at Max Planck Institute for Informatics. His research focuses on computer vision, computational linguistics, and developing trustworthy AI systems.

His work explores multimodal learning, video understanding, and improving AI reliability. Recent publications demonstrate strong emphasis on video-language integration, fact verification systems, and developing methods for AI abstention when uncertain. Research consistently addresses challenges in cross-modal alignment and trustworthy reasoning.

Dr. Rohrbach maintains an active publication record in top-tier venues, with recent work focusing on video instruction understanding, multimodal fact-checking, and efficient pretraining techniques. His contributions advance both theoretical frameworks and practical applications in trustworthy vision-language systems.