R1-Onevision 数据集是由浙江大学于 2025 年发布的，旨在赋予模型高级的多模态推理能力，相关 Blog 为「R1-Onevision：Open-Source Multimodal Large Language Model with Reasoning Ability」。它通过在自然场景、科学、数学问题、基于 OCR 的内容和复杂图表等多个领域的丰富、上下文感知的推理任务，弥合视觉和文本理解之间的差距。

Citation

If you find this code useful for your research, please use the following BibTeX entry. “`python @article{yang2025r1onevision, title={R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization}, author={Yi Yang and Xiaoxuan He and Hongkun Pan and Xiyan Jiang and Yan Deng and Xingtao Yang and Haoyu Lu and Dacheng Yin and Fengyun Rao and Minfeng Zhu and Bo Zhang and Wei Chen}, journal={arXiv preprint arXiv:2503.10615}, year={2025}, }