5 papers
Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement
Tian Wu, Liming Wang, Zijian Wen +5
The emergence of Mixture-of-Experts (MoE) has transformed the scaling of large language models by enabling vast model capacity through sparse activation. Yet, converting these perf…
Electrically Pumped Terahertz Frequency Comb Based on Actively Mode-locked Resonant Tunneling Diode
Feifan Han, Xiongbin Yu, Qun Zhang +6
Terahertz (THz) frequency combs (TFCs) are promising for numerous applications in spectroscopy, metrology, sensing, and wireless communications. However, the practical applications…
Broadband Terahertz Frequency Comb Based on Actively Mode Locked Resonant Tunneling Diode
Feifan Han, Hongxin Zhou, Qun Zhang +9
The frequency combs characterized by their phase-coherent equidistant spectral modes and precise frequency scales of broadband spectrum, have made them an indispensable part of con…
TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction
Weijie Liu, Ziwei Zhan, Carlee Joe-Wong +5
Non-independent and identically distributed (Non-IID) data across edge clients have long posed significant challenges to federated learning (FL) training in edge computing environm…
Online Location Planning for AI-Defined Vehicles: Optimizing Joint Tasks of Order Serving and Spatio-Temporal Heterogeneous Model Fine-Tuning
Bokeng Zheng, Bo Rao, Tianxiang Zhu +5
Advances in artificial intelligence (AI) including foundation models (FMs), are increasingly transforming human society, with smart city driving the evolution of urban living.Meanw…