Kecheng Liang, Xinyu Li, Weixing Chen, Yang Liu. GeoGRPO: Investigating the Stepwise-GRPO Enhancement in RLHF Framework. In Lianwen Jin, Richard Zanibbi, Veronique Eglin, editors, Document Analysis and Recognition - ICDAR 2025 Workshops - Wuhan, China, September 20-21, 2025, Proceedings, Part I. Volume 16225 of Lecture Notes in Computer Science, pages 344-361, Springer, 2025. [doi]
Abstract is missing.