The Institute of Automation of the Chinese Academy of Sciences officially released the "Zidong Taichu" full mode large model

[Global Network Technology Comprehensive Report] On June 16, at the Artificial Intelligence Framework Ecological Summit 2023, Xu Bo, director of the Institute of Automation of the Chinese Academy of Sciences, officially released the full mode model of "Zidong Taichu".It is reported that the "Zidong Taichu" full mode large model is a 2

[Global Network Technology Comprehensive Report] On June 16, at the Artificial Intelligence Framework Ecological Summit 2023, Xu Bo, director of the Institute of Automation of the Chinese Academy of Sciences, officially released the full mode model of "Zidong Taichu".

It is reported that the "Zidong Taichu" full mode large model is a 2.0 version upgraded from the 100 billion parameter multi-mode large model "Zidong Taichu" 1.0. On the basis of voice, image and text three modes, it adds video, sensor signal, 3D point cloud and other modal data. It has broken through the key technologies such as multimodal correlation for cognitive enhancement, and has full mode understanding, generation and correlation capabilities, Accelerate the implementation of universal artificial intelligence in the digital economy era.

Xu Bo demonstrated for the first time in real-time the new functions of the large model in music understanding and generation, 3D scene navigation, signal understanding, multimodal dialogue, and invited on-site audiences to interact with the large model in real-time. The 'Zidong Taichu' full modal cognitive model can not only talk about Beethoven's story through 'Moonlight Song', but also achieve precise positioning in three-dimensional scenes. It can also complete scene analysis through the combination of images and sound.

It is reported that "Zidong Taichu" 2.0 can understand important information in the digital Internet of Things era such as 3D scenes and sensing signals, and achieve cross modal alignment between music, images, and videos. It can handle multimodal related application requirements such as music and video analysis and 3D navigation, and can also achieve multimodal content understanding and generation such as music and videos.

At present, the "Zidong Taichu" big model has shown broad industrial application prospects, and has started a series of leading and exemplary applications in Neurosurgery surgery navigation, short video content review, legal consultation, medical multimodal differential diagnosis, traffic violation image study and other fields.

Xu Bo stated that automation is based on the "Zidong Taichu" large model, continuously exploring the integration of technological paths such as brain like intelligence and game intelligence, and ultimately achieving a universal artificial intelligence that can evolve independently. And we will explore leveraging empowerment value in more fields to contribute to the rapid development of China's digital economy.

Disclaimer: The content of this article is sourced from the internet. The copyright of the text, images, and other materials belongs to the original author. The platform reprints the materials for the purpose of conveying more information. The content of the article is for reference and learning only, and should not be used for commercial purposes. If it infringes on your legitimate rights and interests, please contact us promptly and we will handle it as soon as possible! We respect copyright and are committed to protecting it. Thank you for sharing.(Email:[email protected])