Read news on multimodal model with our app.
Read more in the app
Mistral releases Pixtral 12B, its first multimodal model
Transfusion: Predict the next token and diffuse images with one multimodal model
Meta introduces Chameleon, a state-of-the-art multimodal model
PaliGemma: Open-Source Multimodal Model by Google
Elon Musk’s xAI previews Grok-1.5V, its first multimodal model