Kolja Bauer

PhD
Ludwig Maximilian University of Munich (LMU Munich)
Advancing generative models towards multi-modality and fine-grained controllability

This PhD project focuses on advancing generative models within the field of computer vision. While generative models have achieved impressive results in the domain of image generation, their application beyond images, e.g. to video and 3D data, is still in its infancy. Modeling video and 3D data will enable models to learn more comprehensive world knowledge and support more abstract reasoning. Additionally, a key challenge remains in providing users with fine-grained control over the generation process. This project aims to tackle these issues by exploring novel model architectures and efficient training paradigms.

Track:
Industry Track
ELLIS Edge Newsletter
Join the 6,000+ people who get the monthly newsletter filled with the latest news, jobs, events and insights from the ELLIS Network.