作者位次 #4/5ICLR 2026Poster· Reinforcement Learning / Everything Else
OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
Kaizhuo Yan · YingJie Yu · Yifan Yu · Haizhong Zheng · Fan Lai
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。
Kaizhuo Yan · YingJie Yu · Yifan Yu · Haizhong Zheng · Fan Lai
Zhuoming Chen · Hongyi Liu · Yang Zhou · Haizhong Zheng · Beidi Chen
Haizhong Zheng · Jiawei Zhao · Beidi Chen
Yibo Peng · James Song · Lei Li · Xinyu Yang · Mihai Christodorescu · Ravi Mangal · Corina S. Pasareanu · Haizhong Zheng · Beidi Chen
Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In this paper, we reveal a novel type of threat to real-world code-agents: functionally correct yet vulnerable (FCV) patch...