6 papers
Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference
Zhiyao Xu, Aoxue Liu, Zhanjie Ding +3
Sparsely activated Mixture-of-Experts (MoE) models scale capacity via conditional computation, but distributed inference suffers from cross-GPU expert communication and routing-ind…
State-resolved multimodal contributions to stratospheric polar vortex predictability
Shuo Yang, Dan Zhao, Tingting Xue +3
The dynamical basis of stratospheric polar vortex predictability remains unclear, particularly the relative roles of persistence, structural variability, and cross-level coupling.…
Intelligence Delivery Network: Toward an Internet Architecture for the AI Age
Hanling Wang, Qing Li, Dan Zhao +7
The rapid emergence of AI-powered applications is reshaping the role of the Internet. Users increasingly rely on the network to obtain intelligence services derived from large foun…
Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes
Zhiyao Xu, Dan Zhao, Qingsong Zou +4
As smart homes become increasingly prevalent, intelligent models are widely used for tasks such as anomaly detection and behavior prediction. These models are typically trained on…
FedORGP: Guiding Heterogeneous Federated Learning with Orthogonality Regularization on Global Prototypes
Fucheng Guo, Zeyu Luan, Qing Li +2
Federated Learning (FL) has emerged as an essential framework for distributed machine learning, especially with its potential for privacy-preserving data processing. However, exist…
Synthetic User Behavior Sequence Generation with Large Language Models for Smart Homes
Zhiyao Xu, Dan Zhao, Qingsong Zou +4
In recent years, as smart home systems have become more widespread, security concerns within these environments have become a growing threat. Currently, most smart home security so…