AI Glossary

Vision-language model

Also called VLM

What does “Vision-language model” mean?

Vision-language model: A multimodal model that combines visual understanding with language. It usually pairs an image encoder with a language model so it can answer questions about images, read text in screenshots, or describe what a scene shows.

Vision-language model visual guide: A multimodal model that combines visual understanding with language. It usually pairs an image encoder with a language model so it can answer questions about images, read text in screenshots, or describe what a scene shows.
Visual guide Open full size (new tab)

What is an example of “Vision-language model”?

Tools that let an AI agent read a web page from a screenshot, or explain a diagram in a textbook, typically rely on a vision-language model.

Keep learning

See also

Multimodal AITermVision transformerTermLarge language modelTermComputer useTerm

Same topic

Variational autoencoderTermTransformerTermState-space modelTermSmall language modelTermSelf-attentionTerm