TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards 文章

ArXiv CS.CV2026-06-03NEWSen作者: Mingxuan Cui, Jingpu Yang, Fengxian Ji, Qian Jiang, Zhecheng Shi, Jiaming Wang, Zirui Song, Fajri Koto, Xiuying Chen
查看原文 →
关系图谱

TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards · 相关技术

相关技术

Direct Preference OptimizationGroup Relative Policy OptimizationTextAlign