# Typhoon OCR: Open Vision-Language Model For Thai Document Extraction

arXiv: https://arxiv.org/abs/2601.14722 · HTML: https://mlsanity.com/paper/2601.14722/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 21 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

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

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation](https://mlsanity.com/paper/2502.14846/) (2025)
- [PyThaiNLP: Thai Natural Language Processing in Python](https://mlsanity.com/paper/2312.04649/) (2023)
- [Augraphy: A Data Augmentation Library for Document Images](https://mlsanity.com/paper/2208.14558/) (2022)
- [ChartCap: Mitigating Hallucination of Dense Chart Captioning](https://mlsanity.com/paper/2508.03164/) (2025)
- [OCR Improves Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2202.13274/) (2022)
- [ThaiOCRBench: A Task-Diverse Benchmark for Vision-Language Understanding in Thai](https://mlsanity.com/paper/2511.04479/) (2025)

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

- [How Far Can Synthetic Data Take Thai OCR?](https://mlsanity.com/paper/2609.03595/) (2026)

## Abstract (arXiv)

Document extraction is a core component of digital workflows, yet existing vision-language models (VLMs) predominantly favor high-resource languages. Thai presents additional challenges due to script complexity from non-latin letters, the absence of explicit word boundaries, and the prevalence of highly unstructured real-world documents, limiting the effectiveness of current open-source models. This paper presents Typhoon OCR, an open VLM for document extraction tailored for Thai and English. The model is fine-tuned from vision-language backbones using a Thai-focused training dataset. The dataset is developed using a multi-stage data construction pipeline that combines traditional OCR, VLM-based restructuring, and curated synthetic data. Typhoon OCR is a unified framework capable of text transcription, layout reconstruction, and document-level structural consistency. The latest iteration of our model, Typhoon OCR V1.5, is a compact and inference-efficient model designed to reduce reliance on metadata and simplify deployment. Comprehensive evaluations across diverse Thai document categories, including financial reports, government forms, books, infographics, and handwritten documents, show that Typhoon OCR achieves performance comparable to or exceeding larger frontier proprietary models, despite substantially lower computational cost. The results demonstrate that open vision-language OCR models can achieve accurate text extraction and layout reconstruction for Thai documents, reaching performance comparable to proprietary systems while remaining lightweight and deployable.