Glossary

Modality in AI means different data forms—text, audio, images, or video—each offering unique information that helps models better interpret and respond to inputs.

Multimodal learning enables AI to understand and connect information from text, images, and audio for deeper and more human like comprehension.

Tokenization breaks text into small units called tokens, helping AI models understand, process, and generate language more accurately.

Continual learning allows AI models to learn from new data without forgetting past knowledge, keeping systems efficient and relevant over time.