World-R1: Reinforcing 3D Constraints for Text-to-Video Generation 文章

ArXiv CS.CV2026-05-27NEWSen作者: Weijie Wang, Xiaoxuan He, Youping Gu, Yifan Yang, Zeyu Zhang, Yefei He, Yanbo Ding, Xirui Hu, Donny Y. Chen, Zhiyuan He, Yuqing Yang, Bohan Zhuang
大语言模型
查看原文 →
关系图谱

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation · 相关技术

相关技术

TTEODEPLAlanguage model远程代码执行（RCE）reinforcement learningdivide-and-conquer partitioningalignmentVLMUCTStraight-Through EstimatorScalaReferring expression comprehension (REC)Parts-of-Speech (POS) tagsMITVision-Language ModelsIMUHISGRPOGEOFoundation ModelsForDiTANN