PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training 文章

ArXiv CS.CV2026-06-03NEWSen作者: Zelun Zhang, Hongen Liu, Suyin Liang, Yubo Zhang, Yiqing Xiang, Jiaxuan Liu, Ting Sun, Manhui Lin, Yue Zhang, Changda Zhou, Tingquan Gao, Cheng Cui, Yi Liu, Dianhai Yu, Yanjun Ma
查看原文 →
关系图谱

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training · 相关技术

相关技术

reinforcement learningprogressive post-training reciperegion-aware data optimization framework