LoRA (machine learning)

Parameter-efficient fine-tuning technique for large language models

📊 Rating

1 news mentions · 👍 0 likes · 👎 0 dislikes

📌 Topics

Machine Learning (1)
Federated Learning (1)
Wireless Technology (1)
Natural Language Processing (1)

🏷️ Keywords

Federated Learning (1) · LoRA (1) · Large Language Models (1) · Decentralized Systems (1) · Wireless Communication (1) · Multi-task Learning (1) · Sparse-and-Orthogonal (1) · Mobile Devices (1)

📖 Key Information

LoRA (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique for large language models and other deep neural networks. Introduced in 2021 by researchers at Microsoft, LoRA enables adaptation of pre-trained models to specific tasks while requiring significantly fewer computational resources and trainable parameters than traditional full model fine-tuning.

📰 Related News (1)

🇺🇸 Wireless Federated Multi-Task LLM Fine-Tuning via Sparse-and-Orthogonal LoRA (2026-02-25)
arXiv:2602.20492v1 Announce Type: cross Abstract: Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices w...

🔗 Entity Intersection Graph

People and organizations frequently mentioned alongside LoRA (machine learning):

Wireless · 1 shared articles
🌐
Large language model · 1 shared articles