🔥牛了！微信正式开源端到端文档解析模型 WeVisDoc，一张图直接变 Markdown！
This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
🔥牛了！微信正式开源端到端文档解析模型 WeVisDoc，一张图直接变 Markdown！ 整页图片一次输出完整 Markdown：正文走 Markdown，公式走 LaTeX，表格走 HTML。拍照合同、翻拍论文、扫描报表都能直接吃。 关键亮点： 🔹单模型端到端：版面理解、文字识别、公式识别、表格重建全包，无需流水线 🔹双版本开源：2B 轻量好部署，4B 打退化页面更稳 🔹OmniDocBench v1.6：95.38，端到端组第一 🔹PureDocBench 三赛道均值：75.54，Clean / Digital / Real 全第一 🔹公式和表格是最大优势，脏图上比很多流水线更扛造 🔹基于 Qwen3-VL-2B/4B，Apache-2.0 论文：https://arxiv.org/abs/2609.20423 GitHub：https://github.com/Tencent/WeVisDoc HF：Tencent/WeVisDoc-2B / WeVisDoc-4B #WeVisDoc #开源 #文档解析 #OCR #RAG #微信 #腾讯AI #WeChat
Posted by SuSu_酥酥👅 (15.6k followers) 1 days ago · 160 likes · 20.9k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: arXiv.org, wevisdoc, wemm-embedding, arXiv.org.
More dev work like this
- Maestro v2.3 is out! — @blizaine
- Crucix pulls satellite fire detection, flight tracking, and economic data from 27… — @tom_doerr
- SAM 3.1 is out! It's open source and available through the Meta API and Hugging Face for… — @mattdeitke
- In honor of my new puppy, here is a Doberman tattooing spots on a Dalmatian. 8 seconds,… — @WescheNex1q
- we have chatgpt image 2.0 at home — @zainhas
- This greenscreen tool VFX artists have wanted for 30 years, solved at the pixel. — @0x0SojalSec
- 30 sec MiniMax H3 clip generated locally w/ a 4-step fused ref2va (omni) model in… — @blizaine
- Nano Banana 2.5 is incoming soon from @GoogleDeepMind. 🔥 — @mark_k
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 17.6k posts from 4.9k X accounts over the last 21 days, 2k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 02:20 UTC. Full method.