cs.LG（2024-07-08）

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	A Survey on LoRA of Large Language Models	LoRA综述：对大语言模型低秩适应微调方法进行全面梳理与分析	large language model	✅
2	BoRA: Bayesian Hierarchical Low-Rank Adaption for Multi-Task Large Language Models	提出BoRA以解决多任务大语言模型微调中的信息共享问题	large language model
3	If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers	提出基于层间过滤器的木马防御方法，有效消除预训练语言模型中的未知后门	large language model
4	Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation	提出Sub-SA，通过子模选择性标注提升上下文学习效果并降低标注成本	large language model

#	题目	一句话要点	标签	🔗	⭐
5	B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory	B'MOJO：融合显式和隐式记忆的混合状态空间模型，提升长序列建模能力	Mamba SSM state space model
6	Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control	分析多任务表示学习在动态环境下的后悔值以优化控制策略	representation learning