PT$^2$-LLM: Post-Training Ternarization for Large Language Models
Xianglong Yan · ChengZhu Bao · Zhiteng Li · Tianao Zhang · Kaicheng Yang · Haotong Qin · Ruobing Xie · Samm Sun · Yulun Zhang
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。
Xianglong Yan · ChengZhu Bao · Zhiteng Li · Tianao Zhang · Kaicheng Yang · Haotong Qin · Ruobing Xie · Samm Sun · Yulun Zhang
Wenhong Zhu · Ruobing Xie · Rui Wang · Samm Sun · Di Wang · Pengfei Liu
Haoru Tan · Sitong Wu · Yanfeng Chen · Jun Xia · Ruobing Xie · Bin Xia · Samm Sun · XIAOJUAN QI
Haoru Tan · Sitong Wu · Yanfeng Chen · Shizhen Zhao · Yang-Tian Sun · Tianjia Liu · Chirui Chang · Shaofeng Zhang · Samm Sun · Xiuzhe Wu · Ruobing Xie · XIAOJUAN QI
Songhao Wu · Ang Lv · Ruobing Xie · Samm Sun · Di Wang · Rui Yan · Yankai Lin
Mixture-of-Experts (MoE) models rely on an external router to assign tokens to experts. This design inherently separates the routing decision from each expert’s internal capabilities, leading to suboptimal performance. In this work, we address this limitation with Union-of-Experts (UoE), an MoE v...