# AlibabaResearch/AdvancedLiterateMachinery

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Repository: https://github.com/AlibabaResearch/AdvancedLiterateMachinery
Canonical: https://ross.abutalabs.com/products/advancedliteratemachinery
Language: C++
License: Apache-2.0
License Family: permissive
Topics: artificial-intelligence, documentai, multimodal, multimodal-deep-learning, ocr, computer-vision, vision-language-transformer, end-to-end-ocr, scene-text-detection, scene-text-detection-recognition, scene-text-recognition, text-detection, text-recognition, vision-language, document, document-analysis, document-recognition, document-understanding, document-intelligence, vision-language-model
Last push: 2026-03-17T02:55:55+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 72, release rhythm 8, longevity 100
- inputs: {"age_days": 1435, "days_push": 169, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1834, forks 197 (observed 2026-08-28T04:05:42.528594+00:00)

## What it is
A collection of original OCR and document understanding models, algorithms, and benchmarks from Alibaba's Tongyi Lab, including models like Platypus and the CC-OCR benchmark for evaluating large multimodal models. It provides research code and pretrained models for reading text from images and documents.

## Use cases
- extract text from images with ocr
- recognize scene text in photos
- parse and understand documents
- evaluate multimodal llms on ocr benchmarks
- extract key information from scanned documents
- generate synthetic images containing text
- multilingual text recognition

## When to choose
- you need state-of-the-art OCR or document parsing models
- you want to benchmark large multimodal models on OCR tasks
- you are researching scene text detection, recognition, or visual text generation
- you need key information extraction from documents

## When to avoid
- you need a simple production OCR API with commercial support
- you want a lightweight plug-and-play text extraction tool without GPU resources
- your project is unrelated to text reading or document intelligence

## Facets
- artifact type: library
- maturity: active
- function: ocr, computer-vision, machine-learning, nlp, data-science
- domain: computer-vision, artificial-intelligence, image-processing, pdf
- platform: python, cpp
- tags: document-ai, scene-text-recognition, vision-language-models, benchmark, research-code, multimodal, natural-language-processing, linux, gpu

## Member repositories
- AlibabaResearch/AdvancedLiterateMachinery (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:42.528594+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:18:33.149574+00:00, confidence not recorded.
  - readme: https://github.com/AlibabaResearch/AdvancedLiterateMachinery (fetched 2026-08-28T04:05:42.528594+00:00, sha be8640ffe746)
- Data as of 2026-08-30T08:39:29.467469+00:00.