4 papers
FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning
Yuan Yao, Lixu Wang, Jiaqi Wu +7
Federated learning (FL) enables collaborative training across clients while preserving privacy. While most existing FL methods assume homogeneous model architectures, client hetero…
How Implicit Bias Accumulates and Propagates in LLM Long-term Memory
Yiming Ma, Lixu Wang, Lionel Z. Wang +6
Long-term memory mechanisms enable Large Language Models (LLMs) to maintain continuity and personalization across extended interaction lifecycles, but they also introduce new and u…
A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networks
Jiaqi Wu, Jing Liu, Yang Liu +6
The proliferation of Internet of things (IoT) devices in smart cities, transportation, healthcare, and industrial applications, coupled with the explosive growth of AI-driven servi…
Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment
Jiaqi Wu, Shihao Zhang, Simin Chen +7
Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios. However, existing edge detection methods face challenge…