Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
This work addresses the need for large-scale, specialized AI models in scientific fields like chemistry and life sciences, representing a significant scaling effort rather than an incremental improvement.
The paper tackles the challenge of scaling a scientific multimodal foundation model to one trillion parameters, achieving comprehensive enhancements in general and scientific domains, including mastering over 100 specialized tasks and outperforming proprietary models in scientific depth.
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.