作者位次 #2/4ICML 2026Spotlight· Social Aspects / Safety
Jailbreak to Protect: Buffering Harmful Fine-Tuning via Temporary Jailbreaking LoRA in Large Language Models
Seokil Ham · Jaehyuk Jang · Wonjun Lee · Changick Kim
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。
Seokil Ham · Jaehyuk Jang · Wonjun Lee · Changick Kim
Jaehyuk Jang · Wonjun Lee · Kangwook Ko · Changick Kim
Prompt tuning has achieved remarkable progress in vision–language models (VLMs) and is recently being adopted for audio–language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that conventional prompt tuning for ALMs also suffers from the Base...