Caesar AI Atlas

Multimodal Model

Caesar AI Atlas Definition

A multimodal model is a model designed to accept, relate, or generate data from multiple modalities. Such models may connect language with images, audio, video, tabular data, or other inputs to perform tasks requiring cross-modal understanding.

Other Definitions

Multimodal Model Source

A model whose inputs, outputs, or both include more than one modality. For example, consider a model that takes both an image and a text caption (two modalities) as features, and outputs a score indicating how appropriate the text caption is for the image. So, this model's inputs are multimodal and the output is unimodal.

Related Terms