SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning
SAMoRA:基于语义的LoRA专家混合方法用于任务自适应学习
机构 * School of Computer Science and Technology, Beijing Jiaotong University, China(北京交通大学计算机科学与技术学院) ; Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, China(广西trusted软件重点实验室,桂林电子科技大学) ; Beijing Key Lab of Traffic Data Mining and Embodied Intelligence, China(北京交通数据挖掘与具身智能重点实验室) ; Institute of AI for Industries, Chinese Academy of Sciences, China(工业人工智能研究院,中国科学院) ; Nanjing Institute of Software Technology, China(南京软件技术研究院)
专题命中 指令微调 :large language model(abstract);language model(abstract);分类 cs.CL、cs.AI
AI总结 SAMoRA通过语义感知路由和任务自适应缩放机制,提升多任务学习中的专家专业化与任务适应性,实验显示其性能优于现有方法。
Comments ACL 2026 Findings