Xinyu Yuan

Ph.D. student, College of Computer Science and Technology, Zhejiang University
Email: yxy5315@gmail.com

I am pursuing my Ph.D. at Zhejiang University, where I am part of the ArcLab research group led by Prof. Wenzhi Chen.

Before that, I received my M.Eng. and B.Eng. from the School of Artificial Intelligence at Hefei University of Technology and School of Information and Artificial Intelligence at Anhui Agricultual University respectively, advised by Assoc. Prof. Yan Qiao.

My primary research interests includes network systems, machine learning, AI-generated content (AIGC) and embodied intelligence. I am actively working on the (networking) sevices computing and applications empowered by machine learning. I am also working on studying of the powerful generative models, e.g., diffusions and LLMs.

Download my CV

Publications

  • Diffusion Models Meet Network Management: Improving Traffic Matrix Analysis with Diffusion-based Approach
    Xinyu Yuan, Yan Qiao*, Zhenchun Wei et al.
    IEEE Transactions on Network and Service Management (TNSM), April, 2025
    [Paper] [Code]
  • AutoTomo: Learning-Based Traffic Estimator Incorporating Network Tomography
    Yan Qiao*, Kui Wu, Xinyu Yuan
    IEEE/ACM Transactions on Networking (TON), December, 2024
    [Paper] [Code]
  • Diffusion-TS: Interpretable Diffusion for General Time Series Generation
    Xinyu Yuan, Yan Qiao*
    International Conference on Learning Representations (ICLR), Vienna, Austria, 2024
    [Paper] [Code]
  • Routing-Oblivious Network Tomography with Flow-Based Generative Model
    Yan Qiao*, Xinyu Yuan, Kui Wu
    IEEE International Conference on Computer Communications (INFOCOM), Vancouver, Canada, 2024
    [Paper] [Code]
  • Unsupervised Anomaly Detection for Multivariate Time Series using Diffusion Model
    Rongyao Hu, Xinyu Yuan, Yan Qiao* et al.
    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, 2024
    [Paper] [Code]
  • Traffic Matrix Estimation based on Denoising Diffusion Probabilistic Model
    Xinyu Yuan, Yan Qiao*, Pei Zhao et al.
    IEEE Symposium on Computers and Communications (ISCC), Tunis, Tunisia, 2023
    [Paper] [Code]

Workshop Papers and Preprints

  • Learning-based Sketches for Frequency Estimation in Data Streams without Ground Truth
    Xinyu Yuan, Yan Qiao*, Meng Li et al.
    IEEE Transactions on Knowledge and Data Engineering (TKDE), Under Review
    [Preprint] [Code]

Patents

Services

  • Reviewer: NeurIPS, ICLR, IEEE Transactions on Dependable and Secure Computing (TDSC), IEEE Transactions on Network and Service Management (TNSM), Computer Networks (CN), Knowledge-Based Systems (KBS)

Contact Me

yxy5315 at gmail dot com