# NAMER: Non-Autoregressive Modeling for Handwritten Mathematical Expression Recognition

arXiv: https://arxiv.org/abs/2407.11380 · HTML: https://mlsanity.com/paper/2407.11380/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 54 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [Modeling Coverage for Neural Machine Translation](https://mlsanity.com/paper/1601.04811/) (2016)
- [Image-to-Markup Generation with Coarse-to-Fine Attention](https://mlsanity.com/paper/1609.04938/) (2016)
- [Text Recognition in the Wild: A Survey](https://mlsanity.com/paper/2005.03492/) (2020)
- [2D-CTC for Scene Text Recognition](https://mlsanity.com/paper/1907.09705/) (2019)
- [IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition](https://mlsanity.com/paper/2312.11923/) (2023)
- [Bidirectional Trained Tree-Structured Decoder for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2401.00435/) (2023)

## Built on by (most cited first, 3 of 3)

- [TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2408.08578/) (2024)
- [MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2502.05557/) (2025)
- [GryphOne: Symbol-Aware Masked Diffusion for Structural Refinement in Offline Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2602.03370/) (2026)

## Abstract (arXiv)

Recently, Handwritten Mathematical Expression Recognition (HMER) has gained considerable attention in pattern recognition for its diverse applications in document understanding. Current methods typically approach HMER as an image-to-sequence generation task within an autoregressive (AR) encoder-decoder framework. However, these approaches suffer from several drawbacks: 1) a lack of overall language context, limiting information utilization beyond the current decoding step; 2) error accumulation during AR decoding; and 3) slow decoding speed. To tackle these problems, this paper makes the first attempt to build a novel bottom-up Non-AutoRegressive Modeling approach for HMER, called NAMER. NAMER comprises a Visual Aware Tokenizer (VAT) and a Parallel Graph Decoder (PGD). Initially, the VAT tokenizes visible symbols and local relations at a coarse level. Subsequently, the PGD refines all tokens and establishes connectivities in parallel, leveraging comprehensive visual and linguistic contexts. Experiments on CROHME 2014/2016/2019 and HME100K datasets demonstrate that NAMER not only outperforms the current state-of-the-art (SOTA) methods on ExpRate by 1.93%/2.35%/1.49%/0.62%, but also achieves significant speedups of 13.7x and 6.7x faster in decoding time and overall FPS, proving the effectiveness and efficiency of NAMER.