myhloli
Follow
Lists (3)
Stars
All-in-One Development Tool based on PaddlePaddle（飞桨低代码开发工具）
Toolkit for linearizing PDFs for LLM datasets/training
Official implementation of Character Region Awareness for Text Detection (CRAFT)
A new markup-based typesetting system that is powerful and easy to learn.
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.
PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)
OCR, layout analysis, reading order, table recognition in 90+ languages
Reverse Engineering: Decompiling Binary Code with Large Language Models
Generate a comprehensive review from an arXiv paper, then turn it into a blog post. This project powers the website below for the HuggingFace's Daily Papers (https://huggingface.co/papers).
Task-Aware Agent-driven Prompt Optimization Framework
A machine learning software for extracting information from scholarly documents
Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured …
Document Rectification and Illumination Correction using a Patch-based CNN
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
⚡ TabPFN: Foundation Model for Tabular Data ⚡
UniTable: Towards a Unified Table Foundation Model
A model(ing framework) for sample efficient OCR
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
OCR & Document Extraction using vision models
A Comprehensive Benchmark for Document Parsing and Evaluation
基于MinerU的桌面应用程序，MinerU是一款开源的高质量PDF解析工具，基于深度学习技术，可自动提取PDF文档中的文字、表格、图片、公式等内容，并提供丰富的分析、统计、搜索等功能。 本项目为其提供一个简化版本的WebUI，方便用户上传PDF文件，并实时展示提取结果。
Efficient vision foundation models for high-resolution generation and perception.
Tesseract Open Source OCR Engine (main repository)
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.