Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data 文章

ArXiv CS.CV2026-05-27NEWSen作者: Takaki Yamamoto, Chihiro Noguchi, Toshihiro Tanizawa
大语言模型
查看原文 →
关系图谱

Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data · 相关人物

暂无数据