发表机构
ScienceOne AI; Wenge AI（科学一号人工智能; 文阁人工智能）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对科学人工智能模型能力分散问题，提出S1-Omni统一多模态推理模型，基于科学数据统一表示、知识对齐和解码三个核心组件，经训练和评估，在多基准测试中表现出色优于同类模型，为统一科学建模提供实用路径。
AI 中文摘要
我们提出了S1-Omni，一个用于科学理解、预测和生成的统一多模态推理模型。通过特定领域模型、工具增强的语言模型和科学语言模型，科学人工智能取得了显著进展。然而，模型能力仍然高度分散，限制了异构数据、科学定律和专家知识的联合建模。S1-Omni通过将这些能力整合到一个连贯的科学推理模型中来解决这一差距。S1-Omni的架构基于三个核心组件构建：科学数据的统一表示、自然世界知识对齐和特定领域任务的解码。首先，S1-Omni将自然语言指令和科学对象映射到共享表示空间。其次，它将科学定律和专家知识纳入数据构建和训练。第三，它执行特定任务的解码以支持广泛应用。S1-Omni在S1-Omni语料库上进行训练，并在60多个科学基准上进行评估。它在大多数基准上优于GPT-5.5和Gemini-3.1-Pro，并在几个基准上与特定领域模型相匹配或超越。总体而言，S1-Omni为统一科学建模提供了一条实用途径。
英文摘要
We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-specific models, tool-augmented LLMs, and scientific language models. However, model capabilities remain highly fragmented, limiting the joint modeling of heterogeneous data, scientific laws, and expert knowledge. S1-Omni addresses this gap by consolidating these capabilities into a single, coherent scientific reasoning model. The architecture of S1-Omni is built upon three core components: unified representation of scientific data, natural-world knowledge alignment, and decoding for domain-specific tasks. First, S1-Omni maps natural-language instructions and scientific objects, including CIF, SMILES, protein sequences, spectra, and scientific images, into a shared representation space. Second, it incorporates scientific laws and expert knowledge into data construction and training, enabling the model to reason from scientific evidence. Third, it performs task-specific decoding to support a broad range of applications, including property prediction, spectrum-to-molecular generation, protein site and structure prediction, and scientific image generation and editing. S1-Omni is trained on S1-Omni-Corpus, which covers 200 scientific tasks and contains millions of reasoning samples, and is evaluated on over 60 scientific benchmarks. It outperforms GPT-5.5 and Gemini-3.1-Pro on most benchmarks and matches or surpasses domain-specific models on several benchmarks. Overall, S1-Omni provides a practical path toward unified scientific modeling.
