# A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR

arXiv: https://arxiv.org/abs/2604.00725 · HTML: https://mlsanity.com/paper/2604.00725/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Core SSM architectures for language](https://mlsanity.com/ssm/core-ssm-architectures-for-language/)

## Builds on (most cited first, 21 of 21)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://mlsanity.com/paper/2207.06966/) (2022)
- [Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition](https://mlsanity.com/paper/1811.00751/) (2018)
- [Decoupled Attention Network for Text Recognition](https://mlsanity.com/paper/1912.10205/) (2019)
- [VL-Mamba: Exploring State Space Models for Multimodal Learning](https://mlsanity.com/paper/2403.13600/) (2024)
- [DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognition](https://mlsanity.com/paper/2203.12273/) (2022)
- [End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network](https://mlsanity.com/paper/2012.03868/) (2020)
- [Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention](https://mlsanity.com/paper/1604.03286/) (2016)
- [SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition](https://mlsanity.com/paper/2102.08742/) (2021)
- [READ-BAD: A New Dataset and Evaluation Scheme for Baseline Detection in Archival Documents](https://mlsanity.com/paper/1705.03311/) (2017)
- [DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documents](https://mlsanity.com/paper/2407.09103/) (2024)
- [OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus](https://mlsanity.com/paper/1608.02153/) (2016)
- [DocMamba: Efficient Document Pre-training with State Space Model](https://mlsanity.com/paper/2409.11887/) (2024)
- [TextMamba: Scene Text Detector with Mamba](https://mlsanity.com/paper/2512.06657/) (2025)

## Built on by (most cited first, 1 of 1)

- [Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR](https://mlsanity.com/paper/2606.23524/) (2026)

## Abstract (arXiv)

End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity limits efficient paragraph-level transcription and large-scale deployment. We investigate linear-time State-Space Models (SSMs), specifically Mamba, as a scalable alternative to Transformer-based sequence modeling for OCR. We present to our knowledge, the first OCR architecture based on SSMs, combining a CNN visual encoder with bi-directional and autoregressive Mamba sequence modeling, and conduct a large-scale benchmark comparing SSMs with Transformer- and BiLSTM-based recognizers. Multiple decoding strategies (CTC, autoregressive, and non-autoregressive) are evaluated under identical training conditions alongside strong neural baselines (VAN, DAN, DANIEL) and widely used off-the-shelf OCR engines (PERO-OCR, Tesseract OCR, TrOCR, Gemini). Experiments on historical newspapers from the Bibliotheque nationale du Luxembourg, with newly released >99% verified gold-standard annotations, and cross-dataset tests on Fraktur and Antiqua lines, show that all neural models achieve low error rates (~2% CER), making computational efficiency the main differentiator. Mamba-based models maintain competitive accuracy while halving inference time and exhibiting superior memory scaling (1.26x vs 2.30x growth at 1000 chars), reaching 6.07% CER at the severely degraded paragraph level compared to 5.24% for DAN, while remaining 2.05x faster. We release code, trained models, and standardized evaluation protocols to enable reproducible research and guide practitioners in large-scale cultural heritage OCR available at https://github.com/MarcoPerson/ssm-ocr-benchmark.