Related papers: CR^2: Cost-Aware Risk-Controlled Routing for Wirel…

Edge service caching can significantly mitigate latency and reduce communication and computing overhead by fetching and initializing services (applications) from clouds. The freshness of cached service data is critical when providing…

Selecting the appropriate model at inference time -- the routing problem -- requires jointly optimizing output quality, cost, latency, and governance constraints. Existing approaches delegate this decision to LLM-based classifiers or…

Federated Learning (FL) over wireless network enables data-conscious services by leveraging the ubiquitous intelligence at network edge for privacy-preserving model training. As the proliferation of context-aware services, the diversified…

Internet of Things (IoT) is considered as the enabling platform for a variety of promising applications, such as smart transportation and smart city, where massive devices are interconnected for data collection and processing. These IoT…

To enable large model (LM) based edge intelligent service provisioning, on-device fine-tuning with locally personalized data allows for continuous and privacy-preserving LM customization. In this paper, we propose RingAda, a collaborative…

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under…

Federated Learning (FL) provides a privacy-preserving framework for training machine learning models on mobile edge devices. Traditional FL algorithms, e.g., FedAvg, impose a heavy communication workload on these devices. To mitigate this…

Real-time AI experiences call for on-device large language models (OD-LLMs) optimized for efficient deployment on resource-constrained hardware. The most useful OD-LLMs produce near-real-time responses and exhibit broad hardware…

Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature…

The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent model selection at inference time. While smaller models suffice for routine queries, complex tasks…

We present a framework to analyse the latency budget in wireless systems with Mobile Edge Computing (MEC). Our focus is on teleoperation and telerobotics, as use cases that are representative of mission-critical uplink-intensive IoT systems…

Cooperative inference in Mobile Edge Computing (MEC), achieved by deploying partitioned Deep Neural Network (DNN) models between resource-constrained user equipments (UEs) and edge servers (ESs), has emerged as a promising paradigm.…

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for reducing inference costs and latency. Existing caching…

Machine intelligence on edge devices enables low-latency processing and improved privacy, but is often limited by the energy and delay of moving and converting data. Current systems frequently avoid local model storage by sending queries to…

Mobile cloud and edge computing protocols make it possible to offer computationally heavy applications to mobile devices via computational offloading from devices to nearby edge servers or more powerful, but remote, cloud servers. Previous…

The fifth generation (5G) mobile telecommunication network is expected to support Multi- Access Edge Computing (MEC), which intends to distribute computation tasks and services from the central cloud to the edge clouds. Towards…

Wireless powered mobile edge computing has been envisioned as a promising paradigm to enhance the computation capability of low-power wireless devices in Industrial Internet of Things. An efficient resource scheduling method is critical yet…

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

This study focuses on edge computing in dense millimeter wave vehicle-to-everything (V2X) networks. A control problem is formulated to minimize the energy consumption under delay constraint resulting from vehicle mobility. A tractable…