新突破！微软开源多模态AI Agent，通杀数字、物理世界
今天凌晨3点，微软在官网开源了多模态AI Agent基础模型——Magma。
与传统Agent相比，Magma具备跨数字、物理世界的多模态能力，能自动处理图像、视频、文本等不同类型数据，例如，你可以用Magma来自动下电商订单、查询天气；也可以自动操作实体机器人，或者下真实象棋时获得帮助。
此外，Magma还能内置了心理预测功能，增强了对未来视频帧中时空动态的理解能力，能够准确推测视频中人物或物体的意图和未来行为。
开源地址：https://huggingface.co/microsoft/Magma-8B
github：https://github.com/microsoft/Magma
Magma功能展示
可以用Magma来充当实体机器人的大脑，例如，把蘑菇正确地放在盆里。
Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.
Most Discussed
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10