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。
Qikai Chang · Zhenrong Zhang · Pengfei Hu · Jun Du · Jiefeng Ma · Yicheng Pan · Jianshu Zhang · Quan Liu · Gao Jianqing
Jiawei Liu · Qisi Chen · Jianshu Zhang · Quan Liu · Defu Lian
Large Language Models (LLMs) excel at complex reasoning through search algorithms, yet current strategies often suffer from massive token consumption due to redundant exploration of semantically equivalent steps. Existing semantic similarity methods struggle to accurately identify such equivalenc...
Fei Wu · Zhenrong Zhang · Qikai Chang · Jianshu Zhang · Quan Liu · Jun Du
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via token-level entropy or sequence-level length control, th...