一作ICML 2026Poster· Deep Learning / Large Language Models
Probing RLVR Training Instability through the Lens of Objective-Level Hacking
Yiming Dong · Kun Fu · Haoyu Li · Xinyuan Zhu · Yurou Liu · Lijing Shao · Jieping Ye · Zheng Wang
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。
Yiming Dong · Kun Fu · Haoyu Li · Xinyuan Zhu · Yurou Liu · Lijing Shao · Jieping Ye · Zheng Wang