Meta's Multisensory AI Model Mimics Human Perception with Open-Source ImageBind.

1 min read
Source: The Verge
Meta's Multisensory AI Model Mimics Human Perception with Open-Source ImageBind.
Photo: The Verge
TL;DR

Meta has released an open-source AI model called ImageBind that combines six types of data, including text, audio, visual data, temperature, and movement readings, into a single multidimensional index. The model is a research project with no immediate consumer applications, but it points to a future of generative AI systems that can create immersive, multisensory experiences. Meta's open-source approach to AI research sets it apart from rivals like OpenAI and Google, who have become increasingly secretive.

Share this article

Want the full story? Read the original reporting

Read on The Verge