Model Releases

Shanghai Academy of AI for Science opens multimodal science foundation model "Shenzhen"

Original title:多模态 AI 模型“神珍”开放,能处理蛋白质、天气等六类科学信息

AI summary

The Shanghai Academy of AI for Science has opened "Shenzhen", a multimodal science foundation model with about 11 billion total parameters that can process six types of data: DNA, RNA, proteins, small molecules, Earth systems and medical imaging. On 20 biological sequence tasks, the model achieved the best results in 9; in medical image segmentation it averaged a Dice score of 91.20, the best among 7 evaluated methods. Model weights and code are open on Xinghe Qizhi, Hugging Face and GitHub.

Key Takeaways

  • The Shanghai Academy of AI for Science has opened "Shenzhen",a multimodal science foundation model…
  • On 20 biological sequence tasks,the model achieved the best results in 9
  • in medical image segmentation it averaged a Dice score of 91.
  • 20,the best among 7 evaluated methods.
  • Model weights and code are open on Xinghe Qizhi,Hugging Face and GitHub.

Quick Facts

Published
Updated
Source
IT之家·人工智能
Category
Model Releases
AI score
70
Read the original Read the full article at the original source
Why it matters

一个模型同时理解蛋白质、气象和医学影像,还全开放权重和代码,对交叉学科的研究者是难得的工具包。比专用模型省去切换成本,值得科学计算方向的产品人关注。

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Shanghai Academy of AI for Science opens multimodal science foundation model "Shenzhen". July 20, 2026. https://new.nat6.net/en/news/cmrsxb09d0098bitl4vd2rp04/

View all →