一作ICLR 2026Oral
Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
Houyi Li · Ka Man Lo · Shijie Xuyang · Ziqi Wang · Wenzhen Zheng · Haocheng Zhang · Zhao Li · Shuigeng Zhou · Xiangyu Zhang · Daxin Jiang
效率与系统OpenReview
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。
Houyi Li · Ka Man Lo · Shijie Xuyang · Ziqi Wang · Wenzhen Zheng · Haocheng Zhang · Zhao Li · Shuigeng Zhou · Xiangyu Zhang · Daxin Jiang
Xianzhen Luo · Wenzhen Zheng · Qingfu Zhu · Rongyi Zhang · Houyi Li · Siming Huang · YuanTao Fan · Wanxiang Che
Code Large Language Models (LLMs) are revolutionizing software engineering. However, scaling laws that guide the efficient training are predominantly analyzed on Natural Language (NL). Given the fundamental differences like strict syntax between code and NL, it is unclear whether these laws are d...