作者位次 #2/6ICML 2026Poster· Reinforcement Learning / Everything Else
POLIA: Policy Optimization with Visual-Object-Level Intrinsic Advantage for Multimodal Reasoning
Yiran Zeng · Da Chen · Hangyu Mao · Yuanxing Zhang · Pengfei Wan · Mengchen Zhao
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。
Yiran Zeng · Da Chen · Hangyu Mao · Yuanxing Zhang · Pengfei Wan · Mengchen Zhao