PaliGemma 2 mix is an upgraded vision-language model that supports image captioning, OCR, image Q&A, object detection, and segmentation. With sizes from 3B-28B parameters, there's a model for everyone. Get started. → goo.gle/430HnDe

Google presents: SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Opensources model ckpts with four sizes from 86M to 1B

Google just dropped SigLIP 2 Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Did Google just release a better version of SigLIP? SigLIP 2 is out on Hugging Face! A new family of multilingual vision-language encoders that crush it in zero-shot classification, image-text retrieval, and VLM feature extraction. 🧵👇

This is exciting.... SigLIP was one of the best, highly performant image encoders used for a variety of applications, so a new version of SigLIP from the same team should be pretty good as well!

SigLIP 2 is the most powerful image-text encoder you can use it to do > image-to-image search > text-to-image-search > image-to-text search > image classification with open-ended classes > train vision language models we will show you how to do all this week 🤝

Caught up on the new SigLip 2 paper 🤓 Cool things I learnt from it: - finally using patch size of 16 with size multiple of 256! I was annoyed with weird patch 14 / 224 sizes which felt like old ImageNet training augmentation artifact - reference of LocCa for pretraining which

SigLIP2 is indeed a better encoder than SigLIP! Over the last two weekends, I trained a new SOTA multilingual model - mexma-siglip2. It has not only improved performance but also MIT license. Michael Tschannen Xiaohua Zhai Lucas Beyer (bl16) merve SkalskiP

SigLIP2 + Aya = really good multilingual VLMs!

Excited to release a super capable family of image-text models from our TIPS #ICLR2025 paper! github.com/google-deepmin… We have models from ViT-S to -g, with spatial awareness, suitable to many multimodal AI applications. Can’t wait to see what the community will build with them!

I’m so happy to announce Gemma 3 is out! 🚀 🌏Understands over 140 languages 👀Multimodal with image and video input 🤯LMArena score of 1338! 📏Context window of 128k Available in AI Studio, Hugging Face, Ollama, Vertex, and your favorite OS tools 🚀Download it today!

Think you know Gemini? 🤔 Think again. Meet Gemini 2.5: our most intelligent model 💡 The first release is Pro Experimental, which is state-of-the-art across many benchmarks - meaning it can handle complex problems and give more accurate responses. Try it now →

We are presenting JetFormer at ICLR this morning, poster #190. Stop by if you’re interested in unified multimodal architectures!

Massive advancements in video understanding with Gemini 2.5! ✨ Unlock new capabilities to process hours of video, summarize and retrieve key moments, generate animations, and even combine video with code for interactive experiences. Check the 🧵below for some cool use-cases.

📢 We just released the code for JetFormer at github.com/google-researc… Enjoy!