Mistral AI, a Paris-based artificial intelligence startup, today unveiled its latest advanced AI model capable of processing both images and text. The new model, called Pixtral 12B, employs about 12 ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

French AI startup Mistral has dropped its first multimodal model, Pixtral 12B, capable of processing both images and text. The 12-billion-parameter model, built on Mistral’s existing text-based model ...

The AI industry has long been dominated by text-based large language models (LLMs), but the future lies beyond the written word. Multimodal AI represents the next major wave in artificial intelligence ...

Images are now parsed like language. OCR, visual context and pixel-level quality shape how AI systems interpret and surface content.

H2OVL Mississippi 0.8B Model Surpasses Leading Small Vision Language Models (SVLMs) and Impressively Outperforms Larger State-of-the-Art Vision Language Models (VLMs) in OCR Benchmarks for Text ...

Kling Video O1 Model: A Unified Model for Video/Image Editing and Generation At the heart of the announcement is Video O1, which Kling AI frames as a unified multimodal model built to interpret ...

H2O.ai Inc. on Thursday introduced two small language models, Mississippi 2B and Mississippi 0.8B, that are optimized for multimodal tasks such as extracting text from scanned documents. The models ...

Transformer-based models have rapidly spread from text to speech, vision, and other modalities. This has created challenges for the development of Neural Processing Units (NPUs). NPUs must now ...

After seizing the summer with a blitz of powerful, freely available new open source language and coding focused AI models that matched or in some cases bested closed ...