Touch-R1: Reinforcing Touch Reasoning in MLLMs 文章

ArXiv CS.CV2026-05-27NEWSen作者: Yingxin Lai, Yafei Zhou, Fucai Zhu, Siyu Zhu, Weihao Yuan
大语言模型
查看原文 →
关系图谱

Touch-R1: Reinforcing Touch Reasoning in MLLMs · 相关技术

相关技术

Multimodal Large Language Models (MLLMs)ODELLMlanguage model远程代码执行（RCE）研究法辛烷值多模态sensorreinforcement learningevalReferring expression comprehension (REC)Parts-of-Speech (POS) tagsNATMITLMMICTHISForEffort Metric AttentionARGANN