# Complex Mathematical Expression Recognition: Benchmark, Large-Scale Dataset and Strong Baseline

arXiv: https://arxiv.org/abs/2512.13731 · HTML: https://mlsanity.com/paper/2512.13731/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 14 Dec 2025.

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

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution](https://mlsanity.com/paper/2307.06304/) (2023)
- [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022)
- [Image-to-Markup Generation with Coarse-to-Fine Attention](https://mlsanity.com/paper/1609.04938/) (2016)
- [Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting](https://mlsanity.com/paper/2505.14059/) (2025)
- [CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition](https://mlsanity.com/paper/2111.11011/) (2021)

## Built on by (most cited first, 2 of 2)

- [TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction](https://mlsanity.com/paper/2604.22880/) (2026)
- [MathDoc: Benchmarking Structured Extraction and Active Refusal on Noisy Mathematics Exam Papers](https://mlsanity.com/paper/2601.10104/) (2026)

## Abstract (arXiv)

Mathematical Expression Recognition (MER) has made significant progress in recognizing simple expressions, but the robust recognition of complex mathematical expressions with many tokens and multiple lines remains a formidable challenge. In this paper, we first introduce CMER-Bench, a carefully constructed benchmark that categorizes expressions into three difficulty levels: easy, moderate, and complex. Leveraging CMER-Bench, we conduct a comprehensive evaluation of existing MER models and general-purpose multimodal large language models (MLLMs). The results reveal that while current methods perform well on easy and moderate expressions, their performance degrades significantly when handling complex mathematical expressions, mainly because existing public training datasets are primarily composed of simple samples. In response, we propose MER-17M and CMER-3M that are large-scale datasets emphasizing the recognition of complex mathematical expressions. The datasets provide rich and diverse samples to support the development of accurate and robust complex MER models. Furthermore, to address the challenges posed by the complicated spatial layout of complex expressions, we introduce a novel expression tokenizer, and a new representation called Structured Mathematical Language, which explicitly models the hierarchical and spatial structure of expressions beyond LaTeX format. Based on these, we propose a specialized model named CMERNet, built upon an encoder-decoder architecture and trained on CMER-3M. Experimental results show that CMERNet, with only 125 million parameters, significantly outperforms existing MER models and MLLMs on CMER-Bench.