#EmbeddingGemma

15 stories · 0 in 7 days · 6 in 30 days
Stories, products and papers tagged "EmbeddingGemma", newest first.
Oct 21
Oct 15
Oct 12
Oct 9
ProductsBuildersMulti-source22:09
Chinese contentGoogle 一周发布汇总:SynthID 检测门户全球开放、Nano Banana 2.1、EmbeddingGemma 2 等

Google 一口气发了好几样:SynthID 检测工具全球能用了,Nano Banana 2.1 修图能只改局部,EmbeddingGemma 2 还能在手机上跑多模态嵌入,做开发的可以看看。

Event
官方账号Google AI@GoogleAI7 sourcesSource
Oct 7
ModelsBuildersSelected10:24
Google DeepMind open-sources EmbeddingGemma 2 for on-device multimodal embeddings

The real shift is that embedding models small enough for phones now handle audio and video too, making privacy-first on-device search and RAG practical without cloud calls. Developers building local retrieval or mobile apps can trade a 70–1120 soft-token vision budget against memory. Gains concentrate in code retrieval rather than multilingual text, which only matches the previous version.

shao__meng@shao__mengSource
ModelsBuildersSelected73°05:09
EmbeddingGemma 2: Google's 740M on-device multimodal embedding model

The Apache 2.0 license plus modular encoders mean developers can ship private on-device semantic search without per-query API costs, loading only the components an app needs. It matters for anyone building mobile RAG or personal-data search: the 8K context fits roughly 29 images or 5.5 minutes of audio per query, and code-search gains outpace specialist models twice its size.

rohanpaul_ai@rohanpaul_aiSource
Sep 22