WeChat Vision team open-sources WeVisDoc end-to-end document parser

Tencent WeChat Vision team released WeVisDoc, an end-to-end document parser that takes a page image and outputs structured Markdown with text, LaTeX formulas, HTML tables, and reading order in a single sequence. It uses a two-stage training strategy focused on data allocation, achieving 95.38 on OmniDocBench and showing significant gains on degraded inputs.