works on
edge intelligence 1federated learning 1multimodal large language models 1parameter-efficient fine-tuning 1personalization 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs

Jing Liu, Kun Yang, Yan Wang +5

The paper introduces PFAdapter, a framework that uses hierarchical LoRA decomposition to split adapter parameters into globally shared and locally private parts, enabling efficient…