document-understanding 开源项目推荐（163 个）

deepdoctection /deepdoctection

一个用于 Document AI 的代码仓库

X-PLUG /mPLUG-DocOwl

mPLUG-DocOwl：用于文档理解的模块化多模式大型语言模型

AlibabaResearch /AdvancedLiterateMachinery

面向 Advanced Literate Machinery 的原创、创新想法与算法集合。本项目由阿里巴巴集团通义实验室语言技术实验室 OCR 团队维护。

tstanislawek /awesome-document-understanding

A curated list of resources for Document Understanding (DU) topic

OpenBMB /VisRAG

Parsing-free RAG supported by VLMs

wenwenyu /PICK-pytorch

Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)

jpWang /LiLT

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

GoogleCloudPlatform /document-ai-samples

Sample applications and demos for Document AI, the end-to-end document processing platform on Google Cloud

Tan-Junwen /awesome-table-structure-recognition

A Curated List of Awesome Table Structure Recognition (TSR) Research. Including models, papers, datasets and codes. Continuously updating.

SCUT-DLVCLab /Document-AI-Recommendations

Algorithms, papers, datasets, performance comparisons for Document AI.

huggingface /chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

Alpha-Innovator /DocGenome

DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

andreagemelli /doc2graph

Doc2Graph transforms documents into graphs and exploit a GNN to solve several tasks.

doc-analysis /ReadingBank

ReadingBank: A Benchmark Dataset for Reading Order Detection

dlgjr /FINAR-VL

Open-source financial multimodal LLM for document understanding, chart/table reasoning, numerical reasoning, and financial analysis, with SFT, dual-branch RL, MOPD distillation, and public benchmark evaluation.

cortrix /cortrix

Semantic storage for AI agents. Active pre-release.

LynnHaDo /Document-Layout-Analysis

Object Detection Model for Scanned Documents

athrael-soju /Snappy

🐊 Snappy's unique approach unifies vision-language late interaction with structured OCR for region-level knowledge retrieval. Like the project? Drop a star! ⭐

LynnHaDo /Checkbox-Detection

Checkbox Detection Model for Scanned Documents

microsoft /CompHRDoc

Datasets and Evaluation Scripts for CompHRDoc