Vision-language model (VLM)
Also: Bild-Sprach-Modell
A model that understands images and text together and can, for example, answer questions about a photo.
VLMs combine an image encoder with a language model. They can explain screenshots, read tables from scans, interpret charts or describe product photos.
In businesses they are used for document processing, quality control or accessibility (automatic image descriptions), for example.
General information, not legal or professional advice.