RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarizationby Dongqi Liu, Vera DembergFirst submitted…
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Reportby Justin Zhao, Timothy Wang,…
FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decompositionby Yuxuan Yan, Qianqian Yang,…
FLoRA: Enhancing Vision-Language Models with Parameter-Efficient Federated Learningby Duy Phuong Nguyen, J. Pablo Munoz, Ali…
An empirical study of LLaMA3 quantization: from LLMs to MLLMsby Wei Huang, Xingyu Zheng, Xudong…
Mixture of LoRA Expertsby Xun Wu, Shaohan Huang, Furu WeiFirst submitted to arxiv on: 21…
Personalized Wireless Federated Learning for Large Language Modelsby Feibo Jiang, Li Dong, Siwei Tu, Yubo…
LoRA Dropout as a Sparsity Regularizer for Overfitting Controlby Yang Lin, Xinyu Ma, Xu Chu,…
Personalized Collaborative Fine-Tuning for On-Device Large Language Modelsby Nicolas Wagner, Dongyang Fan, Martin JaggiFirst submitted…
Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformersby Diana-Nicoleta Grigore, Mariana-Iuliana Georgescu,…