# EmbeddingGemma 2: Unified and Efficient Multimodal Representations > Source: > Published: 2026-10-28 15:00:27+00:00 We present EmbeddingGemma 2, an open multimodal embedding model which natively represents text, images, audio, video, and combinations thereof in a unified space. Our approach introduces improvements such as simplified per-layer embeddings and a multi-stage curriculum with modality and objective pro