一作CVPR 2026Poster· Computer Vision & Pattern Recognition
Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection
Jinhu Fu · Yihang Lou · Qingyi Si · Shudong Zhang · Sen Su
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Jinhu Fu · Yihang Lou · Qingyi Si · Shudong Zhang · Sen Su
Jinhu Fu · Yan Bai · Longzhu He · Yihang Lou · Yanxiao Zhao · Li Sun · Sen Su
Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical...