作者位次 #7/9ICLR 2026Poster· Applications / Language, Speech and Dialog
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
Jiachun Li · Pengfei Cao · Zhuoran Jin · Yubo Chen · Jiexin Xu · Huaijun Li · Xiaojian Jiang · Kang Liu · Jun Zhao