一作ICML 2026Poster· Social Aspects / Safety
Learning Efficient Guardrails for Compliance
Xiaofei Wen · Wenjie Mo · Yanan Xie · Peng Qi · Muhao Chen
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。
Xiaofei Wen · Wenjie Mo · Yanan Xie · Peng Qi · Muhao Chen
Wenjie Jacky Mo · Qin Liu · Xiaofei Wen · Dongwon Jung · Hadi Askari · Wenxuan Zhou · Zhe Zhao · Muhao Chen
Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnerable or even malicious code under adversarial settings....