Infinity-Parser2 用多任务强化学习搞定文档解析，开源了500万样本数据集，Pro版在OCR基准上刷新纪录，Flash版速度快3倍多。适合做文档智能处理的开发者。
Infinity-Parser2 是一个大型多模态模型，通过可控数据合成管道和多任务强化学习实现端到端文档解析。研究团队构建并开源了包含500万样本的中英双语数据集Infinity-Doc2-5M，涵盖多种文档类型和标注形式。模型采用8个联合训练目标，包括文档解析、布局分析、表格/数学公式/图表/化学公式解析及文档VQA。Infinity-Parser2-Pro 在olmOCR-Bench上达到87.6%，在ParseBench上达到74.3%，超越DeepSeek-OCR-2、PaddleOCR-VL-1.5和MinerU2.5。Flash变体推理吞吐量较Infinity-Parser-7B提升3.68倍。
Infinity-Parser2 Technical Report
We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold. First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse document types, annotated with element bounding boxes, canonical content forms (Markdown, HTML, LaTeX, SMILES, structured charts), and full-page reading order. Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout analysis, table parsing, math formula parsing, chart parsing, chemical formula parsing, document VQA, and general multimodal understanding), unifying perception, structure, and reasoning in a single optimization signal. Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a $3.68\times$ throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings. Infinity-Parser2-Pro reaches state-of-the-art 87.6% on olmOCR-Bench and 74.3% on ParseBench, surpassing DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU2.5, with strong generalization to charts, chemical formulas, and document VQA.