Related papers: Self-Augmented Mixture-of-Experts for QoS Predicti…
Generative models, such as GPT and BERT, have significantly improved performance in tasks like text generation and summarization. However, hallucinations "where models generate non-factual or misleading content" are especially problematic…
The emergence of new network applications is driving network operators to not only fulfill dynamic bandwidth requirements, but offer various grades of service. Degraded provisioning provides an effective solution to flexibly allocate…
The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…
Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching…
With the explosive growth of the number of services published over the Internet, it is difficult to select satisfactory web services among the candidate web services which provide similar functionalities. Quality of Service (QoS) is…
We present Bayesian Mixture of Experts (Bayesian-MoE), a post-hoc uncertainty estimation framework for fine-tuned large language models (LLMs) based on Mixture-of-Experts architectures. Our method applies a structured Laplace approximation…
The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance. In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different…
Mixture-of-Experts (MoE) models scale capacity via sparse activation but stress memory and bandwidth. Offloading alleviates GPU memory by fetching experts on demand, yet token-level routing causes irregular transfers that make inference…
To satisfy the increasing demand for multimedia services in broadband Internet networks, the WiMAX (Worldwide Interoperability for Microwave Acces) technology has emerged as an alternative to the wired broadband access solutions. It…
Large Mixture of Experts (MoE) models could achieve state-of-the-art quality on various language tasks, including machine translation task, thanks to the efficient model scaling capability with expert parallelism. However, it has brought a…
Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…
Mobile streaming video data accounts for a large and increasing percentage of wireless network traffic. The available bandwidths of modern wireless networks are often unstable, leading to difficulties in delivering smooth, high-quality…
Mixture of Experts (MoE) has emerged as a promising paradigm for scaling model capacity while preserving computational efficiency, particularly in large-scale machine learning architectures such as large language models (LLMs). Recent…
Providing differentiated services to meet the unique requirements of different use cases is a major goal of the fifth generation (5G) telecommunication networks and will be even more critical for future 6G systems. Fulfilling this goal…
This paper studies the uplink and downlink power allocation for interactive augmented reality (AR) services, where the live video captured by an AR device is uploaded to the network edge, and then the augmented video is subsequently…
Managing network complexity, accommodating greater numbers of subscribers, improving coverage to support data services (e.g. email, video, and music downloads), keeping up to speed with fast-changing technology, and driving maximum value…
Mixture-of-Experts (MoE) architectures have become the key to scaling modern LLMs, yet little is understood about how their sparse routing dynamics respond to multilingual data. In this work, we analyze expert routing patterns using…
Service requesters with limited technical knowledge should be able to compare services based on their quality of service (QoS) requirements in cloud service marketplaces. Existing service matching approaches focus on QoS requirements as…
Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…
To ensure safety in teleoperated driving scenarios, communication between vehicles and remote drivers must satisfy strict latency and reliability requirements. In this context, Predictive Quality of Service (PQoS) was investigated as a tool…