一作ICLR 2026Poster· Reinforcement Learning / Function Approximation
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
Xiaoqiang Lin · Arun Verma · Zhongxiang Dai · Daniela Rus · See-Kiong Ng · Bryan Kian Hsiang Low
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。
Xiaoqiang Lin · Arun Verma · Zhongxiang Dai · Daniela Rus · See-Kiong Ng · Bryan Kian Hsiang Low