从像素到精确：利用图像级奖励增强手写数学表达式识别
From Pixel to Precision: Enhancing Handwritten Mathematical Expression Recognition with Image-Level Reward
将图像级视觉奖励（IMS）与GRPO结合，为视觉-语言模型提供更可靠的训练信号，可推广到其他需要渲染保真度的生成任务（如公式识别、图表生成）。
原文依据 we introduce the Image Matching Score (IMS), a lightweight yet effective reward based on the structural edit distance of column-wise image projections
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论手写数学表达式识别受到LaTeX公式双重表示（符号文本与渲染视觉图像）之间根本性错位的阻碍。这种差异意味着文本上不同的LaTeX序列可能产生视觉上相同的输出，而微小的文本错误可能导致灾难性的渲染失败。因此，文本级奖励机制无法完美评估模型预测的质量，无法在训练过程中有效引导模型达到最优性能。为克服这一局限，我们引入了图像匹配分数（IMS），这是一种基于逐列图像投影的结构编辑距离的轻量级且有效的奖励，能够稳健地量化渲染公式之间的视觉保真度。利用IMS，我们进一步提出了图像匹配驱动的策略优化（IMPO），这是一个基于组相对策略优化（GRPO）的训练框架。该方法直接从我们的序列级视觉奖励中促进稳定的策略学习，显著无需单独的价值函数网络。大量实验表明，IMPO在具有挑战性的CROHME、HME100K和M2E数据集上，在不同骨干模型上均带来一致的性能提升。我们的框架建立了新的最优结果，相比强先验方法，表达式识别率平均提升1.1%，最高提升1.37%。
英文原文摘要 1447 字符
Handwritten mathematical expression recognition is hindered by a fundamental misalignment between the dual representations of LaTeX formulas: the symbolic text and the rendered visual image. This discrepancy means that textually distinct LaTeX sequences can produce visually identical outputs, while minor textual errors can cause catastrophic rendering failures. As a result, text-level reward mechanisms cannot perfectly assess the quality of model predictions, failing to effectively guide the model towards optimal performance during training. To overcome this limitation, we introduce the Image Matching Score (IMS), a lightweight yet effective reward based on the structural edit distance of column-wise image projections, which robustly quantifies the visual fidelity between rendered formulas. Leveraging IMS, we then propose Image-Matching driven Policy Optimization (IMPO), a training framework built upon Group Relative Policy Optimization (GRPO). This approach facilitates stable policy learning directly from our sequence-level visual reward, notably without the need for a separate value function network. Extensive experiments demonstrate that IMPO yields consistent performance gains across various backbone models on the challenging CROHME, HME100K, and M2E datasets. Our framework establishes new state-of-the-art results, improving the Expression Recognition Rate by an average of 1.1% and up to 1.37% over strong prior methods.