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。
Tianwei Lin · Zhongwei Qiu · Jie Cao · Jiang Liu · Wenjie Yan · Bo Zhang · Yu Zhong · Wenqiao Zhang · Yingda Xia · Ling Zhang
Jie Cao · Tianwei Lin · Bo Yuan · Rolan Yan · Hongyang He · Wenqiao Zhang · Juncheng Li · Dongping Zhang · Siliang Tang · Yueting Zhuang
Recent studies integrate Low-Rank Adaptation (LoRA) and Mixture-of-Experts (MoE) to further enhance the performance of parameter-efficient fine-tuning (PEFT) methods in Large Language Model (LLM) applications. Existing methods employ homogeneous MoE-LoRA architectures composed of LoRA experts wit...
Jie Cao · Zhenxuan Fan · Zhuonan Wang · Tianwei Lin · Ziyuan ZHAO · Rolan Yan · Wenqiao Zhang · Feifei Shao · Hongwei Wang · Jun Xiao · Siliang Tang
Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT methods, particularly MoE-LoRA architectures, suffer from limited parameter efficiency and coarse-grained adaptation due t...