Meet the CVML Team

Professor for Multimodal Learning at the Tuebingen AI Center and affiliated professor at the MIT-IBM Watson AI Lab. Head of the Computer Vision and Multimodal Learning Group. 

Room A-346, MvL1

Administrative Assistant

Room A-348, MvL1

Grounding for VLMs, Vision-Langauge Explainability, Vision-Language Reasoning

Audio-Video-Language-Models, Mulitmodal Foundation Models

Token compression, Mulitmodal Foundation Models

Multimodal Video Understanding

Efficient Inference for VLMs 

Encoder free VLMs, Discrete VLM Diffusion

Vision-Language Models