Multimodal

Appears in 1 paper · 1 tutorial

Capable of processing and reasoning over multiple modalities (text, images, audio, video) simultaneously.

As used in Paper 20 — Gemini: A Family of Highly Capable Multimodal Models →

Capable of processing and reasoning over multiple modalities (text, images, audio, video) simultaneously. Gemini's key distinguishing feature.

As used in Vector Databases →

Embeddings putting text and images (etc.) in one space for cross-modal search.