Seminar: Multimodal Large Language Models

I contributed as lecturer and supervisor to the installments: SS2024, SS2025

This seminar focuses on cutting-edge research in large language models (LLMs) and multimodal LLMs. Students explore topics such as agentic AI, visual in-context learning, and the integration of language and vision for advanced AI capabilities. Participants independently investigate current developments in these fields, present their findings, and produce detailed written reports. The course emphasizes a deep understanding of multimodal AI approaches, critical analysis of recent research, and effective scientific communication (Website).