AI TrackerGet the app
← All news

Google publishes the EmbeddingGemma 2 technical report

Google has published the technical report for EmbeddingGemma 2, its open embedding model that extends the text-only EmbeddingGemma with native multimodal understanding. The model maps text, images, audio and video, alone or in any combination, into a single embedding space, with a more compact model backbone.

The report covers the training strategy, evaluation methodology and experimental results. Google says the recipe builds on technology from Gemma 4 and Gemini Embedding 2. It also released a five-minute explainer video.

Get news like this as a push.

AI Tracker alerts you when something changes for the tools you use.

Get the app