3 papers
cs.CV2026
Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning
Yuting Ma, Lechao Cheng, Xiaohua Xu
Federated Learning (FL) with pre-trained Vision-Language Models (VLMs) has emerged as a promising paradigm for various downstream tasks. By leveraging its strong representations, r…
cs.CV2024
Modality Alignment Meets Federated Broadcasting
Yuting Ma, Shengeng Tang, Xiaohua Xu +1
Federated learning (FL) has emerged as a powerful approach to safeguard data privacy by training models across distributed edge devices without centralizing local data. Despite adv…
cs.CV2024
FoPru: Focal Pruning for Efficient Large Vision-Language Models
Lei Jiang, Weizhe Huang, Tongxuan Liu +4
Large Vision-Language Models (LVLMs) represent a significant advancement toward achieving superior multimodal capabilities by enabling powerful Large Language Models (LLMs) to unde…