Symbol-Aware Reasoning with Masked Discrete Diffusion for Handwritten Mathematical Expression Recognition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kawakatsu, Takaya, Ishiyama, Ryo
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911418382548992
author Kawakatsu, Takaya
Ishiyama, Ryo
author_facet Kawakatsu, Takaya
Ishiyama, Ryo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03370
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Symbol-Aware Reasoning with Masked Discrete Diffusion for Handwritten Mathematical Expression Recognition
Kawakatsu, Takaya
Ishiyama, Ryo
Computer Vision and Pattern Recognition
Machine Learning
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.
title Symbol-Aware Reasoning with Masked Discrete Diffusion for Handwritten Mathematical Expression Recognition
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2602.03370