5 papers
Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities
Zhixiong Chen, Bingjie Zhu, Jiangzhou Wang +3
Large language models (LLMs) have advanced rapidly, emerging as versatile tools across fields thanks to their exceptional language understanding, generation, and reasoning capabili…
Sampling-Free Diffusion Transformers for Low-Complexity MIMO Channel Estimation
Zhixiong Chen, Hyundong Shin, Arumugam Nallanathan
Diffusion model-based channel estimators have shown impressive performance but suffer from high computational complexity because they rely on iterative reverse sampling. This paper…
Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding
Bingjie Zhu, Zhixiong Chen, Liqiang Zhao +2
Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy.…
Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications
Zhixiong Chen, Hyundong Shin, Arumugam Nallanathan +1
Accurate channel prediction and effective beamforming are essential for low Earth orbit (LEO) satellite communications to enhance system capacity and enable high-speed connectivity…
Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection
Zhixion Chen, Jiangzhou Wang, Hyundong Shin +1
The deployment of unmanned aerial vehicles (UAVs) for reliable and energy-efficient data collection from spatially distributed devices holds great promise in supporting diverse Int…