Tag: Low-Rank Adaptation
All the articles with the tag "Low-Rank Adaptation".
-
Training Plug-n-Play Knowledge Modules with Deep Context Distillation
Published: at 04:28 PM
69.06 🤔本文提出使用深度上下文蒸馏训练可插拔知识模块的方法，能够在低数据场景下高效整合文档知识，并通过实验证明其在问答任务中优于传统方法且与 RAG 具有协同效应。
-
Replay to Remember: Retaining Domain Knowledge in Streaming Language Models
Published: at 04:30 PM 65.14 🤔本文通过结合LoRA和轻量级重放机制的方法，在流式学习条件下帮助大型语言模型减轻灾难性遗忘，同时实现了实时域适应。
-
PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
Published: at 04:28 PM 53.32 🤔本文提出PointLoRA方法，通过低秩适配和多尺度令牌选择，实现点云模型的参数高效微调，显著减少可训练参数同时在多个数据集上达到竞争性性能。