Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

/ Authors

Yi Zou, Dongsheng Zhu, Linchao Zhu, T. Zhu, Yun-Yi Zhou, Peiheng Zhou, Xinyu Zhou, Dongzhan Zhou, Zhiwang Zhou, Yuhao Zhou

and 165 more authors

Bowen Zhou, Zhanping Zhong, Zhijie Zhong, Haiteng Zhao, Penghao Zhao, Xiaomeng Zhao, Zhiyuan Zhao, Yechen Zhang, Jin Zhang, Wenwei Zhang, Hongjie Zhang, Zhu Zhang, Wenlong Zhang, Bo Zhang, Chao Zhang, Chen Zhang, Yuhang Zang, Fei Yuan, Jiakang Yuan, Jiashuo Yu, Jinhui Yin, Haochen Ye, Qian Yao, Bowen Yang, Danni Yang, Kai-Chien Yang, Ziang Yan, Jun Xu, Yichen Xu, Wanghan Xu, Xuenan Xu, Chao Xu, Rui Xu, Shu-Qiao Xing, Long Xing, Xinchen Xie, Ling-I Wu, Zijian Wu, Zhenyu Wu, Lijun Wu, Yue Wu, Jianyu Wu, Wenjie Wu, Fan Wu, Xilin Wei, Q. Wei, Bing-Yu Wang, Rui Wang, Ziyi Wang, Zun Wang, Yi Wang, Haomin Wang, Yizhou Wang, Lintao Wang, Yiheng Wang, Longjian Wang, Bin Wang, Jian Tong, Zhongbo Tian, Huan Tang, Chen Tang, Shi Tang, Yu Sun, Qiushi Sun, Xuerui Su, Qi Su, Chenlin Su, Demin Song, Jinkui Shi, Fukai Shang, Yucheng Ren, Peng Ren, Xiaoye Qu, Yuan Qu, Jiantao Qiu, Yu Qiao, Biqing Qi, Runyu Peng, Tianshuo Peng, Jiahui Peng, Qizhi Pei, Zhuo Pan, Linke Ouyang, Wen Ning, Yi Ma, Zerun Ma, Ning Ma, Runyuan Ma, Chengqi Lyu, Haijun Lv, Han Lv, Lindong Lu, Kuikun Liu, Jiang Liu, Yuhong Liu, Kai Liu, Hongwei Liu, Zhoumianze Liu, Mengjie Liu, Ziyu Liu, Wenran Liu, Yang Liu, Liwei Liu, Kai Liu, Junyao Lin, Junming Lin, Tian Lin, Dahua Lin, Jianze Liang, Linyang Li, Peijie Li, Zonglin Li, Zehao Li, Pengze Li, Guoyan Li, Lingkai Kong, Linglin Jing, Zhe Jin, Feifei Jiang, Qian Jiang, Junhao Huang, Zixian Huang, Haian Huang, Zhouqi Hua, Han Hu, Linfeng Hou, Yinan He, Conghui He, Tianyao He, Xu Guo, Qipeng Guo, Aijia Guo, Yu Gu, Lixin Gu, Jingyang Gong, Qiming Ge, Jiaye Ge, Songyang Gao, Jianfei Gao, Xin Fang, Caihua Fan, Yue Fan, Yanhui Duan, Zichen Ding, Shengyuan Ding, X. Dai, Erfei Cui, Ganqu Cui, Pei Chu, Tao Chu, Guangran Cheng, Yu Cheng, Kai Chen, Yongkang Chen, Chiyu Chen, Guanzhou Chen, Qiaosheng Chen, Si Chen, Xin Chen, Hao Chen, Yicheng Chen, Weihan Cao, Yu Cao, Qinglong Cao, Lei Bai

/ Abstract

We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancement across both general and scientific domains. Beyond stronger reasoning and image-text understanding capabilities, its intelligence is augmented with advanced agent capabilities. Simultaneously, its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields, including chemistry, materials, life sciences, and earth sciences. Achieving this massive scale is made possible by the robust infrastructure support of XTuner and LMDeploy, which facilitates highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level while ensuring strict precision consistency between training and inference. By seamlessly integrating these advancements, Intern-S1-Pro further fortifies the fusion of general and specialized intelligence, working as a Specializable Generalist, demonstrating its position in the top tier of open-source models for general capabilities, while outperforming proprietary models in the depth of specialized scientific tasks.