DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models 文章

ArXiv CS.CV2026-05-26NEWSen作者: Xinrui Shi, Kai Liu, Ziqing Zhang, Jianze Li, Anqi Li, Yulun Zhang
大语言模型
查看原文 →
关系图谱

DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models · 相关人物

暂无数据