Google launches EmbeddingGemma 2, an open multimodal embedding model for devices

Covered by 5 sources
Read the full article
Google released EmbeddingGemma 2, a 740M-parameter open multimodal embedding model that runs entirely on devices like phones, mapping text, code, images, audio, and video into a shared space without cloud reliance. It supports 100+ languages, requires modest memory, and aims to enhance privacy by keeping data local.

Covered by 5 sources


More in Machine Learning

Machine Learning2 min read

Jack Dorsey’s Block made an AI model that talks to you like an awkward new friend

Covered by 5 sources
Machine Learning6 min read

AI21 Labs Releases LIFT-Bench to Curb Reward Hacking in RL Training

Unite.AI

OpenAI Resumes Training AI, But Without Internet Access

Covered by 4 sources