作者位次 #2/8ICML 2026Poster· Social Aspects / Privacy
LMCleaner: Efficient and Certified Online Unlearning via Influence Propagation Truncation
Jie Xu · Zihan Wu · Wenbo Pan · Jiao Yin · Yong-Feng Ge · Hua Wang · Cong Wang · Xiaohua Jia
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。
Jie Xu · Zihan Wu · Wenbo Pan · Jiao Yin · Yong-Feng Ge · Hua Wang · Cong Wang · Xiaohua Jia
Zihan Wu · Jie Xu · Yun Peng · Chun Yong Chong · Xiaohua Jia
Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability patterns undermines the effectiveness of a single unified model, and manual prompt engineering for massive weakness categories is unscalable.To addre...