S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
- URL: http://arxiv.org/abs/2607.15686v1
- Date: Fri, 17 Jul 2026 06:56:08 GMT
- Title: S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
- Abstract summary: We present S1- Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation.<n>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.<n>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.
- Score: 31.901449470705618
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Monkey King Bang: A Unified Scientific Multimodal Foundation Model [26.409792993729948]
We introduce MKB, a unified scientific multimodal model for both understanding and generation.<n> MKB covers six scientific branches, including DNA, RNA, proteins, small molecules, earth science, and medical images.<n>It supports native outputs such as biological sequences, molecular strings, meteorological fields, and segmentation masks.
arXiv Detail & Related papers (2026-07-17T13:56:50Z) - S1-Omni-Image: A Unified Model for Scientific Image Understanding, Generation, and Editing [25.725824689793402]
We present an open-weight unified multimodal model for scientific image understanding, generation, and editing.<n>S1- Omni-Image builds on the scientific multimodal reasoning backbone S1-VL-32B.<n>It supports scientific image understanding, generation, and editing in a unified framework.
arXiv Detail & Related papers (2026-06-23T11:19:34Z) - Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences [89.71422932447423]
LOGOS is a scientific generative language model that unifies heterogeneous tasks across the natural sciences.<n>By representing spatial contact and constraint patterns as discrete tokens, the model captures complex structural interactions in a purely sequential manner.<n>Across diverse tasks, LOGOS consistently matches or outperforms domain-specific baselines.
arXiv Detail & Related papers (2026-06-15T16:14:53Z) - Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models [49.93401412148884]
We introduce FEPBench, a benchmark built from carefully selected high-quality scientific illustrations.<n>We evaluate T2I models along three dimensions: instruction faithfulness, reasoning enrichment, and semantic precision.<n>Results show that even state-of-the-art closed-source models, such as GPT Image 2 and Nano Banana Pro, still suffer from text-rendering bottlenecks, limited reasoning enrichment, and difficulty balancing generation richness with precision.
arXiv Detail & Related papers (2026-06-04T09:49:02Z) - Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale [243.02537333434245]
Intern-S1-Pro is the first one-trillion- parameter scientific multimodal foundation model.<n>Its scientific expertise has been vastly expanded to master over 100 specialized tasks across critical science fields.<n>XTuner and LMDeploy facilitate highly efficient Reinforcement Learning (RL) training at the 1-trillion parameter level.
arXiv Detail & Related papers (2026-03-26T05:21:45Z) - A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers [251.23085679210206]
Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
arXiv Detail & Related papers (2025-08-28T18:30:52Z) - OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery [12.306721865990053]
We introduce OmniScience, a specialized large reasoning model for general science.<n>We develop a battery agent that efficiently ranks molecules as potential electrolyte solvents or additives.<n>We demonstrate via ablation experiments that domain adaptive pretraining and reasoning-based knowledge distillation are critical to attain our performance levels.
arXiv Detail & Related papers (2025-03-22T01:18:59Z) - Nature Language Model: Deciphering the Language of Nature for Scientific Discovery [105.55751854768297]
Foundation models have revolutionized natural language processing and artificial intelligence.<n>We introduce Nature Language Model (NatureLM), a sequence-based science foundation model for scientific discovery.
arXiv Detail & Related papers (2025-02-11T13:08:03Z) - A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery [68.48094108571432]
Large language models (LLMs) have revolutionized the way text and other modalities of data are handled.
We aim to provide a more holistic view of the research landscape by unveiling cross-field and cross-modal connections between scientific LLMs.
arXiv Detail & Related papers (2024-06-16T08:03:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.