Geometry problem-solving remains a significant challenge for Large Multimodal Models (LMMs), requiring not only global shape recognition but also attention to intricate local relationships related to geometric theory. To address this, we propose GeoFocus, a novel framework comprising two core modules. 1) Critical Local Perceptor, which automatically identifies and emphasizes critical local structure (e.g., angles, parallel lines, comparative distances) through thirteen theory-based perception templates, boosting critical local feature coverage by 61% compared to previous methods. 2) VertexLang, a compact topology formal language, encodes global figures through vertex coordinates and connectivity relations. By replacing bulky code-based encodings, VertexLang reduces global perception training time by 20% while improving topology recognition accuracy. When evaluated in Geo3K, GeoQA, and FormalGeo7K, GeoFocus achieves a 4.7% accuracy improvement over leading specialized models and demonstrates superior robustness in MATHVERSE under diverse visual conditions. Project Page -- https://github.com/dle666/GeoFocus

翻译：几何问题求解对大型多模态模型（LMMs）仍是重大挑战，其不仅需要全局形状识别，还需关注与几何理论相关的复杂局部关系。为此，我们提出GeoFocus——一种包含两个核心模块的创新框架。1）关键局部感知器：通过十三个基于理论的感知模板自动识别并强调关键局部结构（如角度、平行线、相对距离），相较于先前方法将关键局部特征覆盖率提升61%。2）VertexLang：一种紧凑的拓扑形式化语言，通过顶点坐标与连接关系编码全局图形。通过替代基于代码的臃肿编码方式，VertexLang在提升拓扑识别精度的同时，将全局感知训练时间减少20%。在Geo3K、GeoQA及FormalGeo7K数据集上的评估表明，GeoFocus较领先的专用模型准确率提升4.7%，并在MATHVERSE中展现出多视觉条件下更优的鲁棒性。项目页面——https://github.com/dle666/GeoFocus