XNews

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

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

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. Based on Qwen3-VL, it uses a two-stage training strategy focusing on coverage then capability allocation, achieving strong performance on degraded documents.

Source posts