Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment 文章

ArXiv CS.AI2026-06-02NEWSen作者: Ran Liu, Min Yu, Mingqi Liu, Jianguo Jiang, Gang Li, Rongsheng Li, Ning Li, Zhen Xu, Weiqing Huang, Ming Liu
查看原文 →
关系图谱

Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment · 相关人物

暂无数据