XHXiaoyao Huang

Xiaoyao Huang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaoyao Huang has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Exploring SLO-Aware GPU Function Overselling in Multi-Tenant FaaS Platforms

    by Yanan Yang, Zhengxiong Jiang, Meiqi Zhu, Hongqiang Xu, Yujun Wang, Liang Li, Jiansong Zhang, Xiaoyao Huang, Yiming Li, Jie Wu

  • Open Access

    Sparsity-Aware Scheduling for Efficient MoE-Based LLM Serving on Edge Servers

    by Yan Zhuang, Chen Gong, Zhenzhe Zheng, Jiale Lei, Xiaoyao Huang, Jie Wu, Fan Wu, Guihai Chen

  • Open Access

    DRAGON: Enhancing On-Device Model Performance with Distributed Retrieval-Augmented Generation

    by Shangyu Liu, Zhenzhe Zheng, Xiaoyao Huang, Fan Wu, Guihai Chen, Jie Wu


  • Open Access

    A Recursive Solution to the Global Maximum Minimum Cut Problem with a Fixed Sink

    by Xiaoyao Huang, Shuo Quan, Jie Wu

    In graph theory and network design, the minimum cut is a fundamental measure of system connectivity and communication capacity. While prior research has largely focused on computing the minimum cut for a fixed source–sink pair, practical scenarios such as data center communication often demand a different objective: identifying the source node whose minimum cut to a designated sink is maximized. This task, which we term the Global Maximum Minimum Cut with Fixed Sink (GMMC-FS) problem, captures the goal of locating a high-capacity source relative to a shared sink node that aggregates multiple servers. The problem is of significant engineering importance, yet it is computationally challenging as it involves a nested max–min optimization. In this paper, we present a recursive reduction (RR) algorithm for solving the GMMC-FS problem. The key idea is to iteratively select pivot nodes, compute their minimum cuts with respect to the sink, and prune dominated candidates whose cut values cannot exceed that of the pivot. By recursively applying this elimination process, RR dramatically reduces the number of max-flow computations required while preserving exact correctness. Compared with classical contraction-based and Gomory–Hu tree approaches that rely on global cut enumeration, the proposed RR framework offers a more direct and scalable mechanism for identifying the source that maximizes the minimum cut to a fixed sink. Its novelty lies in exploiting the structural properties of the sink side of suboptimal cuts, which leads to both theoretical efficiency and empirical robustness across large-scale networks. We provide a rigorous theoretical analysis establishing both correctness and complexity bounds, and we validate the approach through extensive experiments. Results demonstrate that RR consistently achieves optimal solutions while significantly outperforming baseline methods in runtime, particularly on large and dense networks.

  • Open Access

    Joint Prediction and Matching for Computing Resource Exchange Platforms

    by Da Huo, Zhenzhe Zheng, Xiaoyao Huang, Hao Chen, Jianfeng Hu, Zhiyong Yan, Fan Wu, Jie Wu

  • Open Access

    Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance

    by Shangyu Liu, Zhenzhe Zheng, Xiaoyao Huang, Fan Wu, Guihai Chen, Jie Wu

    Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented generation (RAG) is a promising solution to enhance model performance by integrating external databases, without requiring intensive on-device model retraining. However, large-scale public databases and user-specific private contextual documents are typically located on the cloud and the device separately, while existing RAG implementations are primarily centralized. To bridge this gap, we propose DRAGON, a distributed RAG framework to enhance on-device SLMs through both general and personal knowledge without the risk of leaking document privacy. Specifically, DRAGON decomposes multi-document RAG into multiple parallel token generation processes performed independently and locally on the cloud and the device, and employs a newly designed Speculative Aggregation, a dual-side speculative algorithm to avoid frequent output synchronization between the cloud and device. A new scheduling algorithm is further introduced to identify the optimal aggregation side based on real-time network conditions. Evaluations on real-world hardware testbed demonstrate a significant performance improvement of DRAGON-up to 1.9x greater gains over standalone SLM compared to the centralized RAG, substantial reduction in per-token latency, and negligible Time to First Token (TTFT) overhead.

  • Service Coalition Based Joint Application Deployment and Task Assignment for Mobile Edge Computing

    by Xiaoyao Huang, Baoxian Zhang, Guoliang Ji, Cheng Li

    Mobile edge computing (MEC) has been a promising architecture for providing delay-sensitive computing services to mobile users. In the provisioning of MEC services, one big issue is the potential mismatching between dynamic task arrivals and resources allocated for different types of applications at edge servers, which can cause degraded system performance. In this paper, we study the joint optimization of application deployment and task assignment at different time scales in a MEC system constituent of multiple cloudlet service providers. The design objective is to maximize the system profit while meeting the task delay requirements of different applications. We formulate this problem as a mixed integer linear programming (MILP) problem. For the online scenario where future task arrival information is unknown in advance, we propose a multi-armed bandit based application deployment and maximum flow matching based service coalition algorithm. We deduce the complexity of the proposed algorithm and prove that it satisfies individual rationality and coalition rationality. Extensive simulations are carried out and the results show that the proposed algorithm can effectively improve the system profit while satisfying the task delay requirements.


  • Open Access

    Computing Power Network: Multi-Objective Optimization-Based Routing

    by Yunpeng Xie, Xiaoyao Huang, Jingchun Li, Tianhe Liu

    This paper presents a novel routing planning method based on multi-objective optimization to tackle the routing problem in computing power networks. The proposed method aims to improve the performance and efficiency of routing by considering multiple objectives. In this study, we first model the computing power network and formulate the routing problem as a multi-objective optimization problem. To address this problem, we introduce a non-dominated sorting genetic algorithm incorporating a ratio parameter adjustment strategy based on reinforcement learning. Extensive simulations are conducted to evaluate the performance of the proposed routing algorithm. The results demonstrate significant client latency and cost reductions, highlighting the algorithm’s effectiveness. By providing a comprehensive solution to the routing problem in computing power networks, this work contributes to the field by offering improved performance and efficiency. The proposed method’s ability to optimize multiple objectives sets it apart from existing approaches, making it a valuable contribution to the research community.


  • Open Access

    Energy Criticality Avoidance-Based Delay Minimization Ant Colony Algorithm for Task Assignment in Mobile-Server-Assisted Mobile Edge Computing

    by Xiaoyao Huang, Bo Lei, Guoliang Ji, Baoxian Zhang

    Mobile edge computing has been an important computing paradigm for providing delay-sensitive and computation-intensive services to mobile users. In this paper, we study the problem of the joint optimization of task assignment and energy management in a mobile-server-assisted edge computing network, where mobile servers can provide assisted task offloading services on behalf of the fixed servers at the network edge. The design objective is to minimize the system delay. As far as we know, our paper presents the first work that improves the quality of service of the whole system from a long-term aspect by prolonging the operational time of assisted mobile servers. We formulate the system delay minimization problem as a mixed-integer programming (MIP) problem. Due to the NP-hardness of this problem, we propose a dynamic energy criticality avoidance-based delay minimization ant colony algorithm (EACO), which strives for a balance between delay minimization for offloaded tasks and operational time maximization for mobile servers. We present a detailed algorithm design and deduce its computational complexity. We conduct extensive simulations, and the results demonstrate the high performance of the proposed algorithm compared to the benchmark algorithms.