All terms
Multimodal
Multimodal Model
A model that works across more than one data type, such as text and images.
Definition
A multimodal model processes, and sometimes generates, more than one data type—such as text, images, audio, or video—often within a shared representation. It typically bridges specialized encoders to a common backbone so the modalities can be reasoned about together. Modern flagship assistants are usually multimodal, letting people mix text and images in a single request.