Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness 文章

ArXiv CS.CV2026-06-01NEWSen作者: Xiang Fang, Wanlong Fang, Wei Ji
大语言模型
查看原文 →
关系图谱

Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness · 相关人物

暂无数据