一作NeurIPS 2026Poster
Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
Guangyu Yang · Jingbiao Mei · Mingsheng Sun · Jinghong Chen · Yingtong Bu · Pengda Qin · Da Chen · Bill Byrne
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。
Guangyu Yang · Jingbiao Mei · Mingsheng Sun · Jinghong Chen · Yingtong Bu · Pengda Qin · Da Chen · Bill Byrne
Guangyu Yang · Jinghong Chen · Jingbiao Mei · Weizhe Lin · Bill Byrne
Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation to counter emerging attack strategies without costly retr...