2025年9月28日
LRM reward signal 论文两篇
摘要： RLBFF: BINARY FLEXIBLE FEEDBACK TO BRIDGE BETWEEN HUMAN FEEDBACK & VERIFIABLE REWARDS Language Models that Think, Chat Better 阅读全文
posted @ 2025-09-28 14:21 jack-chen666 阅读(16) 评论(0) 推荐(0)