Tencent open-sources WeVisDoc: end-to-end document parsing model turns a page image into Markdown
xiaohu · x · 2026-09-19
Tencent's WeChat Vision team open-sourced WeVisDoc, an end-to-end document parsing model in 2B and 4B variants. One image in, one full-page output: Markdown body text, LaTeX formulas, HTML tables and restored reading order — all from a single VLM with no separate layout detector or OCR engine. The 2B suits resource-limited or clean-page cases; the 4B is stronger on photographed and degraded pages.
Related event: Tencent open-sources WeVisDoc, tops OmniDocBench at 95.38(3 posts)→
More from Multimodal
- First omnimodal embeddings survey maps convergence across text, vision, audio — _reachsumit · 2026-11-04
- Experimental video mixes visual styles, generated with Seedance 2.5 on Adobe Firefly — umesh_ai · 2026-11-04
- Hailuo AI claims H3 scored perfect on language tests; Japanese creator praises its Japanese signage fidelity — Hailuo_AI · 2026-11-04
- YANAMI: 400K-dialog multimodal dataset shows models still fail at stateful multiturn interaction — Shengyu Wang · 2026-11-04
- Open-source Idol model turns a single image into 3D in 45s on 8GB VRAM — Promptmethus · 2026-11-04
- ComfyUI v0.44.0 released with new Patina texture nodes — Fcking_Chuck · 2026-11-04