Infinity-Parser2 Technical Report

Researchers released Infinity-Parser2, a large multimodal model for end-to-end document parsing, along with a 5-million-sample bilingual corpus Infinity-Doc2-5M. The model uses multi-task reinforcement learning across eight objectives and achieves state-of-the-art results on olmOCR-Bench and ParseBench, surpassing existing OCR models.

arXiv:2607.07836v1 Announce Type: new Abstract: 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.