5 papers
Enhanced Structured Lasso Pruning with Class-wise Information
Xiang Liu, Mingchen Li, Xia Li +7
Modern applications require lightweight neural network models. Most existing neural network pruning methods focus on removing unimportant filters; however, these may result in the…
Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference
Xiang Liu, Yijun Song, Xia Li +5
Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown excepti…
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
Leigang Qu, Haochuan Li, Wenjie Wang +4
Large Multimodal Models (LMMs) have demonstrated impressive capabilities in multimodal understanding and generation, pushing forward advancements in text-to-image generation. Howev…
One-shot Federated Learning Methods: A Practical Guide
Xiang Liu, Zhenheng Tang, Xia Li +6
One-shot Federated Learning (OFL) is a distributed machine learning paradigm that constrains client-server communication to a single round, addressing privacy and communication ove…
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
Xiang Liu, Liangxi Liu, Feiyang Ye +4
Efficiently aggregating trained neural networks from local clients into a global model on a server is a widely researched topic in federated learning. Recently, motivated by dimini…