作者位次 #6/6ICML 2026Poster· General Machine Learning / Everything Else
When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
Tong Xie · Ching-Yuan Bai · Yuanhao Ban · Yunqi Hong · Haoyu Li · Cho-Jui Hsieh
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。
Tong Xie · Ching-Yuan Bai · Yuanhao Ban · Yunqi Hong · Haoyu Li · Cho-Jui Hsieh
Zihan Chen · Yiming Zhang · Hengguang Zhou · Zenghui Ding · Yining Sun · Cho-Jui Hsieh
Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs). Despite recent benchmark gains reported for RL, we find that training on these benchmarks’ training sets achieves nearly the same performance as training directly on the test...