Unverified60% confidenceReleaseExact time
Google open-sourced the multimodal embedding model EmbeddingGemma2, which can convert text and images into the same vector space.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
10/7/2026
First Seen
Valid until: 1/5/2027
Sources
Related Entities
Related Claims
UnverifiedEmbeddingGemma 2 is a multimodal embedding model built by Google on the Gemma 4 architecture, capable of encoding text, images, audio, and video into a shared 768-dimensional vector space.78% similarUnverifiedGoogle has released EmbeddingGemma 2, an embedding model with a total of 740M parameters, which is Google's first natively multimodal on-device open-source embedding model.74% similarUnverifiedGoogle's multimodal technology implementation relies on the deep fusion of a real-time visual encoder with a language model, essentially integrating Google Lens's image recognition capability with Gemini's language understanding capability at the underlying level.71% similarUnverifiedGoogle's specialized Gemma models include: EmbeddingGemma for text embedding and semantic search, FunctionGemma for tool calling, PaliGemma focused on vision, and ShieldGemma focused on safety69% similarUnverifiedGoogle的创作工具矩阵包括YouTube、Google Workspace、Google Ads、Veo（视频生成模型）和Imagen（图像生成模型）69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985546API
curl https://kongchang.com/api/v1/knowledge/claims/985546MCP
get_claim(id=985546)