3 papers
cs.CV2026
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini
Madhuri Shanbhogue, Zhe Li, Shanfeng Zhang +86
We introduce Gemini Embedding 2, a native multimodal embedding model that allows embedding video, audio, image, and text modalities in a unified representation space. We leverage t…
cs.CV2026
A Benchmark and Knowledge-Grounded Framework for Advanced Multimodal Personalization Study
Xia Hu, Honglei Zhuang, Brian Potetz +4
The powerful reasoning of modern Vision Language Models open a new frontier for advanced personalization study. However, progress in this area is critically hampered by the lack of…
cs.CL2025
EmbeddingGemma: Powerful and Lightweight Text Representations
Henrique Schechter Vera, Sahil Dua, Biao Zhang +86
We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledg…