Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

Tencent/WeVisDoc

WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.

#Document parsing
Visit GitHub
Python
512
50
3 contributors
Apache License 2.0
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Tencent/WeVisDoc is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 17 – Nov 5, 2026

Stars +832 in 50 days

050100150
142

Forks +50 in 50 days

051015
11

Merged PRs 0 in 50 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Sep 17Sep 24Oct 1Oct 8Oct 15Oct 22Oct 29Nov 5
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+29+10
Sat, Sep 19, 2026+52+00
Sun, Sep 20, 2026+142+110
Mon, Sep 21, 2026+50+00
Tue, Sep 22, 2026+24+20
Wed, Sep 23, 2026+16+00
Thu, Sep 24, 2026+24+00
Fri, Sep 25, 2026+2+10
Sat, Sep 26, 2026+2+00
Sun, Sep 27, 2026+7+00
Mon, Sep 28, 2026+1+00
Tue, Sep 29, 2026+3+10
Wed, Sep 30, 2026+2+00
Thu, Oct 1, 2026+1+00
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+21+10
Mon, Oct 5, 2026+37+30
Tue, Oct 6, 2026+10+10
Wed, Oct 7, 2026+25+10
Thu, Oct 8, 2026+11+10
Fri, Oct 9, 2026+25+10
Sat, Oct 10, 2026+20+10
Sun, Oct 11, 2026+0+10
Mon, Oct 12, 2026+0+20
Tue, Oct 13, 2026+0+60
Wed, Oct 14, 2026+32+20
Thu, Oct 15, 2026+26+50
Fri, Oct 16, 2026+31+10
Sat, Oct 17, 2026+32+20
Sun, Oct 18, 2026+49+30
Mon, Oct 19, 2026+4+00
Tue, Oct 20, 2026+9+00
Wed, Oct 21, 2026+0+10
Thu, Oct 22, 2026+0+10
Fri, Oct 23, 2026+35+00
Sat, Oct 24, 2026+23+00
Sun, Oct 25, 2026+23+10
Mon, Oct 26, 2026+18+00
Tue, Oct 27, 2026+2+00
Wed, Oct 28, 2026+21+00
Thu, Oct 29, 2026+8+00
Fri, Oct 30, 2026+10+00
Sat, Oct 31, 2026+4+00
Sun, Nov 1, 2026+0+00
Mon, Nov 2, 2026+0+00
Tue, Nov 3, 2026+0+00
Wed, Nov 4, 2026+0+00
Thu, Nov 5, 2026+1+00
Total+832+500
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Oct 61 post

    • 文档解析最难的不是认出字，而是把公式、表格和版面关系一起还原。WeVisDoc 用微调后的 Qwen3-VL，把整页图像转成含 LaTeX 公式、HTML 表格的结构化 Markdown： 工程上值得看的是端到端路径：既可用 Transformers 本地推理，也能通过 vLLM 提供服务，并支持批量处理与张量并行。2B、4B 两档便于在算力和解析质量间权衡；但部署仍需 GPU，PDF…

      Read full on X, posted by @vintcessun

      @vintcessun · x.com

  2. 17 days earlier
  3. Sep 191 post

    • If you're building search over scanned reports or research papers, Tencent's WeVisDoc is worth a look. It's an Apache-2.0 document parser in 2B and 4B sizes, built on Qwen3-VL. Feed it a page image…

      Read full on X, posted by @jimmy_longbow_

      @jimmy_longbow_ · x.com

  4. Sep 181 post

    • WeVisDoc-4B 在 OmniDocBench 拿下 95.38 分，四个评测全第一，Real Degraded 上比第一阶段涨了 4.03 分。做法是两步走：先扩语义/结构/外观覆盖加退化合成，再用探针锁定残留弱点定向补数据。搞扫描件解析和 RAG 的可以重点看看。

      Read full on X, posted by @LFrefman

      @LFrefman · x.com

You might also like

Repositories close to Tencent/WeVisDoc
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

chatdoc-com/OCRFlux

Python

OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.

2.5k161

memect/memect-ppx

JavaScript

PDF, Parsing, Agent, IDP, Document, OCR, Python, Layout

508

breezedeus/Pix2Text

Jupyter Notebook

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

3.3k295

facebookresearch/nougat

Python

Implementation of Nougat Neural Optical Understanding for Academic Documents

10.1k646

datalab-to/chandra

Python

OCR model that handles complex tables, forms, handwriting with full layout.

12.7k1.3k

patsnap/Hiro-Smart-Doc

Python

Smart Document API turns PDFs, Office documents, and images into structured layouts, OCR text, tables, formulas, and Markdown for AI-powered document understanding.

262

patsnap/Hiro-MOSS-OCR

Python

0.3B OCR model which emits structured markup ---- math as latex, table as html, text as markdown.

746

Nebutra/MinerU-Skill

Python

AI-Native document parser: PDF, Office & images → clean Markdown with LaTeX, tables & OCR. Zero-dependency CLI & skill for Claude Code, Cursor & AI agents.

1336

bytedance/Dolphin

Python

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

9.1k792