paper-with-me

Papers

Infinity-Parser2 Technical Report

2026-07-08 · Zuming Huang, Jun Huang, Kexuan Ren, Baode Wang, Weizhen Li, Jianming Feng, Yu Wang, Yichen Yao, Shijun Lin, Yige Tang, Cheng Peng, Weidi Xu, Wei Chu, Yinghui Xu, Yuan Qi arxiv

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 3.68x 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.

📄 PDF Abstract BibTeX arXiv:2607.07836

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

2025-06-01 · Baode Wang, Biao Wu, Weizhen Li, Meng Fang 외

Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptab…

Document AIdocument understandingLanguage ModelingLanguage Modelling+4

Uni-Parser Technical Report

2025-12-17 · Xi Fang, Haoyi Tao, Shuwen Yang, Chaozheng Huang 외 arxiv

This technical report introduces Uni-Parser, an industrial-grade document parsing engine tailored for scientific literature and patents, delivering high throughput, robust accuracy, and cost efficiency. Unlike pipeline-b…

Infinity Parser: Layout Aware Reinforcement Learning for Scanned Document Parsing

2025-10-17 · Baode Wang, Biao Wu, Weizhen Li, Meng Fang 외 arxiv

Document parsing from scanned images into structured formats remains a significant challenge due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Existing supervised fine-tuni…

Reinforcement Learning

AMR Parsing is Far from Solved: GrAPES, the Granular AMR Parsing Evaluation Suite

2023-12-06 · Jonas Groschwitz, Shay B. Cohen, Lucia Donatelli, Meaghan Fowlie

We present the Granular AMR Parsing Evaluation Suite (GrAPES), a challenge set for Abstract Meaning Representation (AMR) parsing with accompanying evaluation metrics. AMR parsers now obtain high scores on the standard AM…

Abstract Meaning RepresentationAMR ParsingSentence

An Automated Engineering Assistant: Learning Parsers for Technical Drawings

2019-09-18 · Dries Van Daele, Nicholas Decleyre, Herman Dubois, Wannes Meert

From a set of technical drawings and expert knowledge, we automatically learn a parser to interpret such a drawing. This enables automatic reasoning and learning on top of a large database of technical drawings. In this …