SciIR：一个大规模科学图像推理生成训练数据集与基准

摘要

尽管文本到图像（T2I）模型在生成逼真视觉内容方面取得了显著成功，但在处理科学图像所需的严格语义对齐与逻辑推理时仍存在不足。受皮尔士符号三元组启发，我们提出科学图像推理（SciIR），这是一个用于训练和评估科学图像生成的综合性资源。我们将科学推理形式化为三个核心维度：实体结构（像似符）、科学过程（指示符）和科学定律（规约符）。具体而言，为克服科学图像生成中训练数据稀缺的问题，我们精心构建了SciIR-82k，这是一个包含来自前沿出版物的8万多对高质量科学图文对的大规模数据集。该数据集根据符号维度进行分层组织，并融入了科学推理链式思维（Sci-RCoT），以显式建模底层视觉逻辑。在评估方面，我们提出SciIR-Bench，该基准与这三个符号层次对齐，并采用原子检查表将面向结果的科学准确性转化为面向过程、可验证的细粒度问题。我们的广泛实验揭示了当前模型在科学推理能力上的显著不足。此外，通过在SciIR-82k数据集上进行微调，我们开发了Qwen-Image-SciIR模型，该模型在SciIR-Bench上取得了显著进步，最终得分从35%提升至43%，为科学图像生成的未来发展奠定了坚实基础。

English

While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic alignment and logical reasoning required for scientific imagery. Inspired by Peirce's Semiotic Triad, we introduce Scientific Image Reasoning (SciIR), a comprehensive resource for training and evaluation of scientific image generation. We formalize scientific reasoning into three core dimensions: Entity Structure (Icon), Scientific Process (Index), and Scientific Law (Symbol). Specifically, to overcome the scarcity of training data in scientific image generation, we elaborately create SciIR-82k, a large-scale dataset containing over 80,000 high-quality scientific image-text pairs from cutting-edge publications. The dataset is hierarchically organized according to the semiotic dimensions and incorporates a Scientific Reasoning Chain-of-Thought (Sci-RCoT) to explicitly model underlying visual logic. For evaluation, we propose SciIR-Bench, which aligns with these three semiotic levels and employs an Atomic Checklist to convert the outcome-oriented scientific accuracy into process-oriented, verifiable, fine-grained questions. Our extensive experiments reveal significant deficiencies in current models' scientific reasoning capabilities. Furthermore, by fine-tuning on the SciIR-82k dataset, we developed the Qwen-Image-SciIR model, which achieves a substantial improvement on the SciIR-Bench, increasing the final score from 35\% to 43\%, laying a solid foundation for future advances in scientific image generation.