16 papers
TALSC: Timeliness-Aware Large-Small VLM Collaboration for Infrastructure-Assisted Autonomous Driving
Mengmeng Zhu, Yuxuan Sun, Wei Chen +1
The deployment of Vision-Language Models (VLMs) in autonomous driving (AD) systems is constrained by on-board computing power, restricting vehicles to small VLMs (SVLMs) with limit…
Center-Fed Pinching Antenna System for Uplink Environment Sensing
Cong Yu, Xu Gan, Bo Ai +3
A center-fed pinching antenna system (C-PASS)-enabled uplink environment sensing framework is proposed. Through the center-fed framework, doubled degrees of freedom is achieved com…
ComHymba: Low-Complexity Domain-Informed Foundation Model for Wireless Communications
Bowen Yang, Wei Chen, Jiaming Cheng +1
Wireless foundation models are a promising route to unify channel reconstruction, sensing, and beam management in future wireless communication systems, but existing designs often…
GELATO: Generative Entropy- and Lyapunov-based Adaptive Token Offloading for Device-Edge Speculative LLM Inference
Zengzipeng Tang, Yuxuan Sun, Wei Chen +2
The recent growth of on-device Large Language Model (LLM) inference has driven significant interest in device-edge collaborative LLM inference. As a promising architecture, Specula…
Hierarchical Online-Scheduling for Energy-Efficient Split Inference with Progressive Transmission
Zengzipeng Tang, Yuxuan Sun, Wei Chen +3
Device-edge collaborative inference with Deep Neural Networks (DNNs) faces fundamental trade-offs among accuracy, latency and energy consumption. Current scheduling exhibits two dr…
Timeliness-Oriented Scheduling and Resource Allocation in Multi-Region Collaborative Perception
Mengmeng Zhu, Yuxuan Sun, Yukuan Jia +3
Collaborative perception (CP) is a critical technology in applications like autonomous driving and smart cities. It involves the sharing and fusion of information among sensors to…