OvisOCR2 Tops Document Parsing Leaderboard
OvisOCR2, a 0.8B document parsing VLM fine-tuned from Qwen3.5-0.8B, has topped parsing leaderboards. It aims to convert single-page document images directly into naturally ordered Markdown, covering text, formulas, and tables.
2026-07-15 ~ 2026-07-16 · 2 related posts
- Episode 1: Alibaba Unveils OvisOCR2 for Local Document Parsing(2026-07-13, 4 posts)
- Episode 2: OvisOCR2 Tops Document Parsing Leaderboard(2026-07-15, 2 posts)
- OvisOCR2 Tops Document Parsing Leaderboard — Littlepharaoh · 2026-07-15
- OvisOCR2: End-to-End Document Parsing Model — Shiyin Lu · 2026-07-16