AI engineering glossary · Generative media multimodal
What is VLM (vision-language model)?
Vision-language model (also called VLM): A model that takes images together with text and produces text, for tasks like captioning, visual question answering and document reading. It usually links a vision encoder to a language model through a connector layer.
Vision-language model: an example
A shopkeeper photographs a shelf and asks, 'Which products are almost out of stock?', and the model lists them.
Related terms
More Generative media multimodal terms
- Visual grounding
- Visual instruction tuning
- Visual question answering
- VITS
- Voice activity detection
- Voice cloning
- VQ-VAE
- Wasserstein GAN
Where you learn it
Vision-language model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.