Mojtaba Seyedhosseini (@mseyed) header
Mojtaba Seyedhosseini (@mseyed) profile picture

Mojtaba Seyedhosseini

@mseyed

Gemini Embedding @GoogleDeepMind

Joined July 2010
  • Tweets8
  • Following80
  • Followers267
3Media
Photo by Mojtaba Seyedhosseini (@mseyed)Photo by Mojtaba Seyedhosseini (@mseyed)Photo by Mojtaba Seyedhosseini (@mseyed)
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini 🚀 Today, we’re sharing the @GoogleDeepMind white paper for GE 2, our first native multimodal embedding model. Whether it’s text, audio, video, or image, GE 2 provides a unified representation of the input.
Image from Mojtaba Seyedhosseini (@mseyed)
27
181
20
1,197
115,295
more replies
Read the paper here: arxiv.org/abs/2605.27295
Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini

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 the multimodal...

arxiv.org
1
5
2
41
3,091
Vertex AI: docs.cloud.google.com/gemini… Gemini API: ai.google.dev/gemini-api/doc… We can’t wait to see what the community builds with these new capabilities. 🛠️
Gemini Embedding 2 | Gemini Enterprise Agent Platform | Google Cloud Documentation

Gemini Embedding 2  |  Gemini Enterprise Agent Platform  |  Google Cloud Documentation

Learn about Gemini Embedding 2, Google's omnimodal embedding model designed to generate 3072-dimensional vectors.

docs.cloud.google.com
1
2
18
2,421
Mojtaba Seyedhosseini retweeted
André Araujo (@andrefaraujo) profile picture
André Araujo@andrefaraujoApr 15
True multimodal AI needs to understand the world spatially 🎯 🚀 Excited to release #CVPR2026 TIPSv2 from @GoogleDeepMind, a foundational image-text encoder with spatial awareness, leading to strong overall results and massive gains on patch-text alignment. 🔥 1/N
Image from André Araujo (@andrefaraujo)
11
96
9
732
84,627
Load more