arXivBangrui Xu, Ziyang Miao, Xuanhe Zhou, Yiming Lin, Zirui Tang, Xiaomeng Zhao, Fan Wu, Cheng Tan, Fan Wu, Bin Wang, Conghui HeSun, May 24, 2026, 3:00 AM PDT
score 16.2
Post-processor fixes broken document structures from OCR systems
Original: MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
Source: arxiv.org ↗
Writing ELI5 summary…