PANews 5月10日消息,据科创板日报报道,当地时间9日,Meta公开一个新的开源人工智能模型ImageBind,该模型能够将多种数据流整合在一起,包括文本、音频、视觉数据、温度和运动读数等。该模型目前只是研究项目,还没有直接的消费者或实际应用,但它展示了未来生成式人工智能系统的可能性,这些系统能创造出沉浸式、多感官的体验。
Meta开源多感官人工智能模型ImageBind,整合文本、音频等数据
This article is not available in the current language yet. Showing the original version.
Share to:
Author: PA一线
This content is for market information only and is not investment advice.
Follow PANews official accounts, navigate bull and bear markets together
Recommended Reading
PANews App
24/7 blockchain news tracking and in-depth analysis.

