To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs 文章

ArXiv CS.CV2026-06-02NEWSen作者: Rui Hong, Shuxue Quan
区块链
查看原文 →
关系图谱

To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs · 相关技术

相关技术

TTEODEPLA远程代码执行（RCE）后训练divide-and-conquer partitioningalignmentReferring expression comprehension (REC)Parts-of-Speech (POS) tagsPETORMNATVLMICTForDecodeCodingCamouflaged object detectionANNANGLE