Michael Tschannen

A new framework enhances visual reasoning using language models as controllers.

A new approach improves image captioning with location-aware techniques.

PaliGemma combines image and text understanding for versatile applications.

JetFormer creates images and text together in an efficient way.

VLMs blend vision and language, creating smarter machines that understand the world better.

Discover how Jet transforms noise into stunning images effortlessly.