机构
*
School of Computer Science and Artificial Intelligence, Wuhan University of Technology(武汉理工大学计算机科学与人工智能学院)
;
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)
;
University of Electronic Science and Technology of China(电子科技大学)
;
Wuhan Vocational College of Software and Engineering(武汉软件工程职业学院)
机构
*
School of Mathematics and Sciences, Fudan University(复旦大学数学科学学院)
;
Shanghai Center for Mathematical Sciences, Fudan University(复旦大学上海数学中心)
;
Alibaba Group(阿里巴巴集团)
;
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University(复旦大学类脑智能科学与技术研究院)
;
Center for Applied Mathematics & Shanghai Key Laboratory of Contemporary Applied Mathematics, Fudan University(复旦大学应用数学中心暨上海市现代应用数学重点实验室)
Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
通过因果发现和双模态安全子空间投影诊断和修复视觉-语言模型中的不安全通道
Jinhu Fu, Yihang Lou, Qingyi Si, Shudong Zhang, Yan Bai, Sen Su
机构
*
Beijing University of Posts and Telecommunications(北京邮电大学)
;
Huawei Technologies Ltd.(华为技术有限公司)
;
Peking University(北京大学)
;
Chongqing University of Posts and Telecommunications(重庆邮电大学)
CommentsPaper is currently under review. Authors' version posted for personal use and not for redistribution. Previous version of the preprint was titled: 'AVERY: Adaptive VLM Split Computing through Embodied Self-Awareness for Efficient Disaster Response Systems'