Transformers and LLMs

Multimodal Model, explained

A multimodal model can process or generate more than one kind of data, such as text, images, audio, or video.
Back to Glossary

Part of the Semantic Notion technical glossary.

Short Definition

A multimodal model can process or generate more than one kind of data, such as text, images, audio, or video.

Intuition

Instead of treating every modality as a separate system, the model connects different forms of information in one shared reasoning process.

Technical Definition

A multimodal model maps multiple input or output modalities into compatible representations for joint training, inference, or generation.

Example

A model can read a chart image and answer a text question about the trend.

Common Misunderstandings

Multimodal input does not mean every modality is equally strong.
A model may accept images and audio while still only producing text.

Start here

Need the broader concept map?

Return to the glossary index to move from this definition into adjacent AI, ML, mathematics, and computer science terms.