S1-Omni：面向科學理解、預測與生成的統一多模態推理模型

摘要

我們提出 S1-Omni，一個用於科學理解、預測與生成的統一多模態推理模型。AI for Science (AI4S) 透過領域專用模型、工具增強的 LLM 以及科學語言模型取得了顯著進展。然而，模型能力仍然高度分散，限制了對異質數據、科學定律與專家知識的聯合建模。S1-Omni 透過將這些能力整合到一個單一且連貫的科學推理模型中，填補了這一空白。S1-Omni 的架構建立在三個核心組件之上：科學數據的統一表示、自然世界知識對齊，以及領域特定任務的解碼。首先，S1-Omni 將自然語言指令與科學物件（包括 CIF、SMILES、蛋白質序列、光譜以及科學圖像）映射到一個共享的表示空間。其次，它將科學定律和專家知識融入數據構建與訓練過程中，使模型能夠依據科學證據進行推理。第三，它執行任務特定的解碼，以支援廣泛的應用，包括屬性預測、光譜到分子生成、蛋白質位點與結構預測，以及科學圖像生成與編輯。S1-Omni 在 S1-Omni-Corpus 上進行訓練，該語料庫涵蓋 200 項科學任務並包含數百萬個推理樣本，並在超過 60 個科學基準測試上進行評估。它在大多數基準測試上優於 GPT-5.5 和 Gemini-3.1-Pro，並在多項基準測試上達到或超越領域專用模型的表現。總體而言，S1-Omni 為實現統一的科學建模提供了一條實用路徑。

English

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.