@denziideng: Absolutely great! 35.6k-star open-source and free, PDF translation messes up formats? This one preserves layout perfectly! After translating scientific papers, formulas and charts all messed up? Layout ruined and hard to read? The core of the scientific PDF document translation and bilingual comparison tool PDFMathTranslate is right here: complete layout preservation: formulas, charts, tables...
Summary
PDFMathTranslate is an open-source, free scientific PDF document translation tool that perfectly preserves layout, formulas, charts, etc., supports multiple languages and AI translation, and offers CLI/GUI/Docker usage.
View Cached Full Text
Cached at: 08/23/26, 09:37 AM
PDFMathTranslate
-
What does this do?
-
Recent Updates
-
Use 🌟
3.1 Online Service 🌟
3.2 Local Installation
- Technical Details
4.2 Downstream Development
4.3 Differences between two major forks
- Project Information
5.1 Citation
5.2 Acknowledgement
5.3 Contributors
5.4 Star History
Similar Articles
@Ryrenz: Throwing PDFs directly into large models? Tables get garbled, formulas break, and scanned documents can't even be read. These 5 tools help you convert documents into a clean format that AI can digest. 1. Stirling-PDF — All-in-one local PDF toolbox, 85k stars. Merge, split, compress, add watermarks, convert formats, dozens of operations…
This article introduces 5 open-source tools for converting documents into AI-readable formats: Stirling-PDF, MinerU, docling, marker, and OCRmyPDF, respectively targeting PDF editing, complex document conversion to Markdown, structured document output, high-precision PDF to Markdown, and OCR for scanned documents.
PDFMathTranslate: Scientific Document Translation Preserving Layouts
This paper introduces PDFMathTranslate, an open-source tool for translating scientific documents while preserving their original layout, leveraging large language models and precise layout detection.
@amiaoapp: Tired of slogging through foreign literature and tech blogs? Every time you copy a PDF paragraph into a web translator, you get gibberish line breaks and messy formatting. Have to manually delete spaces and newlines line by line? Infuriatingly slow. Ditch this archaic copy-paste nightmare and send it to the shredder! Recommend a Git…
Recommend an open-source real-time translation tool, CopyTranslator. It supports cross-platform, automatically handles line-break garbled text from PDF copying, enabling copy-to-translate and boosting foreign literature reading efficiency.
@heynavtoor: Rongxin Ouyang solved the one problem every researcher outside the English-speaking world has been silently suffering f…
PDFMathTranslate is an open-source tool that translates scientific PDFs while preserving math formulas, charts, tables, and layout, accepted at EMNLP 2025 and freely available under MIT license.
@Ryrenz: Papers, contracts, PDFs — these open-source tools cover all document work: 1. opendatalab/MinerU (68.9k) — from Shanghai AI Lab, one-click PDF/document to markdown, excellent academic paper layout restoration. https://github.c…
This tweet summarizes 6 open-source tools covering PDF to markdown, document understanding, OCR, paper translation, and automatic literature review, aiming to streamline document workflows.