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。
Zhuoqun Li · Boxi Cao · Guiping Jiang · Fangrui Lv · Ruotong Pan · Jianan Wang · Xiangyu Wu · Hongyu Lin · Yaojie Lu · Yong Du · Ruyin Jia · Liyan · Tingting Gao · Han Li · Xianpei Han · Le Sun
Can Xie · Ruotong Pan · Xiangyu Wu · Zhang yunfei · Jiayi Fu · Tingting Gao · Guorui Zhou
Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). However, prevailing algorithms like GRPO broadcast a uniform advantage signal across all tokens in a sequence. This coarse-grained approach...