10 papers
Split-Gate Pooled-Evidence Stochastic-Rollout Scheduling for Timely Progressive Edge Inference
Sai Xu, Yinbo Yu, Yanan Du +2
This paper investigates causal radio scheduling for progressive edge inference, with the goal of maximizing timely inference throughput under job-specific deadlines. Specifically,…
Uplink-Completion-Triggered Edge-GPU Inference for Multi-Agent Cooperative Perception
Sai Xu, Yanan Du, Chong Tang +1
This paper investigates the coupling between wireless input completion and graphics processing unit (GPU) execution in centralized multi-agent cooperative perception. Specifically,…
Joint Scheduling of Sensing Data Offloading and Edge Inference for Multi-UAV Networks
Yanan Du, Sai Xu, Yinbo Yu
Unmanned aerial vehicles (UAVs) often collaborate by collecting and offloading sensing streams to an edge server, where a deep neural network (DNN) model performs cross-stream alig…
Joint Scheduling of Multi-Band Radar Sensing and DNN Inference for Cross-Stage Parallelism
Yanan Du, Sai Xu, Kezhi Wang +1
This paper studies end-to-end latency minimization for a multi-band radar sensing and deep neural network (DNN) inference pipeline. Unlike conventional stage-wise designs that trea…
Orchestrating Multimodal DNN Workloads in Wireless Neural Processing
Sai Xu, Kai-Kit Wong, Yanan Du +1
In edge inference, wireless resource allocation and accelerator-level deep neural network (DNN) scheduling have yet to be co-optimized in an end-to-end manner. The lack of coordina…
Using STAR-IRS to Secure Indoor Communications Through Symbol-Level Random Phase Modulation
Yanan Du, Zeyang Sun, Yilan Zhang +2
This paper proposes a secure indoor communication scheme based on simultaneous transmitting and reflecting intelligent reflecting surface (STAR-IRS). Specifically, a transmitter (A…
WiNPA: Wireless Neural Processing Architecture
Sai Xu, Yanan Du
This article presents a wireless neural processing architecture (WiNPA), providing a novel perspective for accelerating edge inference of deep neural network (DNN) workloads via jo…
A Graph-based Hybrid Beamforming Framework for MIMO Cell-Free ISAC Networks
Yanan Du, Sai Xu, Jagmohan Chauhan
This paper develops a graph-based hybrid beamforming framework for multiple-input multiple-output (MIMO) cell-free integrated sensing and communication (ISAC) networks. Specificall…
Toward Practical Fluid Antenna Systems: Co-Optimizing Hardware and Software for Port Selection and Beamforming
Sai Xu, Kai-Kit Wong, Yanan Du +4
This paper proposes a hardware-software co-design approach to efficiently optimize beamforming and port selection in fluid antenna systems (FASs). To begin with, a fluid-antenna (F…
GSM: A GNN-based Space-MIMO Framework for Direct-to-Cell Communications
Sai Xu, Yanan Du, Gaojie Chen +1
This paper proposes a graph neural network (GNN)-based space multiple-input multiple-output (MIMO) framework, named GSM, for direct-to-cell communications, aiming to achieve distri…