Knowledge Category

Multimodal

17 October 2026 · 1 min read

EmbeddingGemma 2: Open, Lightweight Multimodal Embedding Model

Summary: Google DeepMind announced EmbeddingGemma 2, a new open-source and lightweight multimodal embedding model. This model aims to represent different data types (text, image, etc.) in a single vector space. …

#ai #machine-learning #embeddings #open-source #multimodal

17 October 2026 · 1 min read

Introducing Gemini 3.8 Live with Live Avatar

Summary: Google DeepMind introduced the Gemini 3.8 Live model and its “Live Avatar” feature. This new capability aims to provide more interactive and real-time experiences with artificial intelligence. Gemini 3.8 Live …

#ai #real-time #multimodal #user-experience #low-latency