Ming-Jun Duan

Accelerating Federated LoRA Fine-Tuning for LLMs with Adaptive Ranks at Network Edge

The rapid development of large language models (LLMs) has played a crucial role in advancing artificial intelligence. Pretrained LLMs can be adapted to various downstream tasks through fine-tuning. To alleviate the intensive resource requirements of fine-tuning and safeguard data privacy, researchers have integrated Lo...