GryphOne: 面向离线手写数学表达式识别中结构细化的符号感知掩码扩散
GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition
AI总结：
提出离散扩散框架GryphOne，将HMER重构为迭代符号细化而非序列生成，通过符号感知分词和随机掩码互学习提升鲁棒性，在MathWriting上达到5.51% CER和59.9% EM，超越所有重实现模型和商业系统。
摘要：
手写数学表达式识别（HMER）需要对多样化的符号和结构进行推理，然而自回归模型存在曝光偏差和语法不一致的问题。我们提出GryphOne，一个离散扩散框架，将HMER重构为迭代符号细化而非序列生成。GryphOne逐步细化符号和关系，消除自回归并提高一致性。符号感知分词和随机掩码互学习进一步增强了对手写多样性的鲁棒性。在MathWriting基准上，GryphOne实现了5.51%的字符错误率（CER）和59.9%的完全匹配率（ExpRate），在匹配设置下优于所有重实现模型以及商业HMER系统。在CROHME 2014-2023上的保留评估进一步展示了强大的跨数据集泛化能力。
英文摘要：
Handwritten mathematical expression recognition (HMER) requires reasoning over diverse symbols and structures, yet autoregressive models struggle with exposure bias and syntax inconsistency. We present GryphOne, a discrete diffusion framework which reformulates HMER as iterative symbolic refinement instead of sequential generation. GryphOne progressively refines symbols and relations, removing autoregression and improving consistency. Symbol-aware tokenization and random-masking mutual learning further enhance robustness to handwriting diversity. On the MathWriting benchmark, GryphOne achieves 5.51% CER and 59.9% EM (ExpRate), outperforming all reimplemented models in the matched setting as well as the commercial HMER system. Held-out evaluation on CROHME 2014-2023 further shows strong cross-dataset generalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
