14 papers
From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing
Jutao Xiao, Yuan Qu, Dongsheng Ma +7
Recent document parsers achieve table TEDS scores above 93 on OmniDocBench v1.6, yet community feedback and our audit reveal persistent failures on complex real-world tables. To qu…
MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition
Haote Yang, Jiang Wu, Jingchao Wang +42
In organic chemistry papers and patents, molecular structures, reaction schemes, and experimental conditions are often presented as molecular structure depictions, reaction diagram…
MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation
Zhiyuan Zhao, Bin Wang, Linke Ouyang +5
In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine…
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
Bangrui Xu, Ziyang Miao, Xuanhe Zhou +7
VLM-based OCR models have become the de facto choice for document parsing, as they can accurately extract page-level elements (e.g., paragraphs within individual pages) together wi…
MolRecBench-Wild: A Real-World Benchmark for Optical Chemical Structure Recognition
Haote Yang, Hui Wang, Chen Zhu +14
Optical Chemical Structure Recognition (OCSR) aims to translate molecular diagrams in scientific literature into machine-readable formats, but current systems remain unreliable on…
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Bin Wang, Tianyao He, Linke Ouyang +40
Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art…