The second new model that Microsoft released today, Phi-4-multimodal, is an upgraded version of Phi-4-mini with 5.6 billion parameters. It can process not only text but also images, audio and video.

Transformers are more than meets the eye ... For this reason, many familiar state-of-the-art models, such the GPT family, are decoder only. Encoder-decoder models combine both components ...

Microsoft is expanding its Phi line of open-source language models with two new algorithms optimized for multimodal ...

In earlier work, the team trained a system, including a transformer model similar to ... And the original brain decoder only works on people for whom it was trained. With this latest work, the ...