SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning 文章

ArXiv CS.CV2026-05-27NEWSen作者: Philip Schroeder, Thomas Weng, Karl Schmeckpeper, Eric Rosen, Stephen Hart, Ondrej Biza
大语言模型
查看原文 →
关系图谱

SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning · 相关技术

相关技术

ORMODEPLAlanguage model远程代码执行（RCE）研究法辛烷值reinforcement learningevalVerseStraight-Through EstimatorSPAReferring expression comprehension (REC)Narrative Abstraction BenchmarkNLINATVision-Language ModelsVLMIoTForENADensechain-of-thoughtCoTANNRAW