PaperCodex

MonkeyOCR: High-Accuracy Document Parsing for Complex Layouts with Tables, Formulas, and Multilingual Text—Fast, Lightweight, and Deployable 6354

Parsing complex documents—especially those containing tables, mathematical formulas, mixed layouts, or multilingual content—remains a persistent challenge in real-world AI applications.…

12/11/202512/15/2025Document Parsing, Optical Character Recognition (OCR), vision-language modeling

Easy Dataset: Turn PDFs, Docs, and Wikis into High-Quality LLM Fine-Tuning Data Visually and Efficiently 12323

Large language models (LLMs) are remarkably capable—but they often stumble when applied to specialized domains like finance, legal, healthcare, or…

12/10/202512/15/2025Domain-specific Question Answering, LLM fine-tuning Data Synthesis, Structured Dataset Generation

WebDancer: Build Autonomous Web Agents That Solve Complex, Multi-Step Research Tasks 17544

Most large language models today give one-shot answers—but real-world problems rarely fit into a single prompt. Imagine trying to answer:…

12/10/202512/15/2025Autonomous Information Seeking, Multi-step Research Automation, Web-based Reasoning Agents

PDFMathTranslate: Translate Scientific PDFs Without Losing Formulas, Layouts, or Meaning 30427

Translating scientific documents has always been a frustrating experience—especially when the output PDF ends up with scrambled equations, broken tables,…

11/15/202512/15/2025Layout-preserving Translation, Multilingual Technical Document Processing, Scientific Document Translation