Abstract
Handwritten Mathematical Expression Recognition (HMER) requires reasoning over diverse symbols and 2D structural layouts, yet autoregressive models struggle with exposure bias and syntactic inconsistency. We present a discrete diffusion framework that reformulates HMER as iterative symbolic refinement instead of sequential generation. Through multi-step remasking, the proposal progressively refines both symbols and structural relations, removing causal dependencies and improving structural consistency. A symbol-aware tokenization and Random-Masking Mutual Learning further enhance syntactic alignment and robustness to handwriting diversity. On the MathWriting benchmark, the proposal achieves 5.56\% CER and 60.42\% EM, outperforming strong Transformer and commercial baselines. Consistent gains on CROHME 2014--2023 demonstrate that discrete diffusion provides a new paradigm for structure-aware visual recognition beyond generative modeling.
Abstract (translated)
手写数学表达式识别（HMER）需要对各种符号和二维结构布局进行推理，然而自回归模型在处理曝光偏差和语法不一致性时存在困难。我们提出了一种离散扩散框架，将HMER重新表述为迭代符号细化过程，而不是顺序生成过程。通过多步重掩码技术，该方法逐步优化符号及其结构关系，消除了因果依赖性，并提高了结构的一致性。符号感知的标记化和随机掩码互学习进一步增强了语法对齐能力，并提升了对手写多样性鲁棒性的表现。在MathWriting基准测试中，我们的方案实现了5.56% 的字符错误率（CER）和60.42% 的精确匹配度（EM），超越了强大的Transformer模型及商业基线模型的性能。在CROHME 2014-2023数据集上的持续改进表明，离散扩散为结构感知型视觉识别提供了一种新的范式，超越了传统的生成建模方法。 这段描述详细介绍了如何通过离散扩散框架来解决手写数学表达式的识别问题，并强调这种方法在处理符号语法一致性和结构布局方面优于传统自回归模型。此外，文中提到的实验结果表明该技术在现有基准测试中表现出色，为未来的视觉识别任务提供了新的研究方向。
URL
https://arxiv.org/abs/2602.03370
