智东西China AI News(@Chinazhidx):Alibaba has open-sourced Logics-Parsing-V3, a 0.8B VLM for structured long-document parsing. Instead of resetting at every page, it carries a compact structural state forward as it reads — preserving context across pages without putting the entire document into one context window. This lets it recover document hierarchy, merge content split across pages, and link visual elements to related text in a single end-to-end model. It also handles complex layouts, scientific formulas, and chemical notation. On MPDocBench-Parse, it scores 85.26, ranking #1

智东西China AI News

@Chinazhidx

Zhidongxi is China's leading AI industry media outlet, providing news and insights on China's LLMs, robotics, AI agents, AI applications, and AI Hardware.

参加 February 2026

89 フォロー中 2.6K ファン

智东西China AI News@Chinazhidx

2026.09.23 07:44

Alibaba has open-sourced Logics-Parsing-V3, a 0.8B VLM for structured long-document parsing. Instead of resetting at every page, it carries a compact structural state forward as it reads — preserving context across pages without putting the entire document into one context window. This lets it recover document hierarchy, merge content split across pages, and link visual elements to related text in a single end-to-end model. It also handles complex layouts, scientific formulas, and chemical notation. On MPDocBench-Parse, it scores 85.26, ranking #1# — 4.46 points ahead of PaddleOCR-VL-1.5