EmbeddingGemma 2: Unified and Efficient Multimodal Representations

Google released EmbeddingGemma 2, an open multimodal embedding model that natively represents text, images, audio, video, and combinations of those modalities in a unified space. The model introduces simplified per-layer embeddings and a multi-stage curriculum with modality and objective pro[gression].

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