Yongqiang Huang
Yongqiang Huang
(黄永强)
Ph.D. Student
Sichuan University
Cyber Science and Engineering
yqhuang2912(at)gmail.com
Education
  • Sichuan University
    Sichuan University
    2024 - Present
    Ph.D., Cyber Science and Engineering
    Chengdu, China
  • Sichuan University
    Sichuan University
    2018 - 2021
    M.S., Computer Science
    Chengdu, China
  • Sichuan University
    Sichuan University
    2014 - 2018
    B.S., Electronics and Information Engineering
    Chengdu, China
    • Experience
  • Huawei Cloud Computing Technology Co., Ltd.
    Huawei Cloud Computing Technology Co., Ltd.
    2021 - 2024
    Software Engineer
    China
    • Services
    • Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI, IJCAI, ACM MM, MICCAI, ISBI, BIBM
    • Journal Reviewer: TPAMI, TIP, TMI, TNNLS, TMM, TRPMS, PR, TOIS, JBHI, MEDIA
    About Me

    I am a Ph.D. student in Cyber Science and Engineering at Sichuan University. My research focuses on federated learning, image generation, and AI for healthcare.

    I am especially interested in representation learning for distributed, privacy-sensitive, and clinically complex settings: how models can learn from heterogeneous clients, preserve useful local knowledge, and still build robust global representations. My recent work spans federated visual learning, reliable multi-label medical image diagnosis, and LLM-orchestrated CT reconstruction, while my earlier work studied deep learning methods for MRI reconstruction, CT reconstruction and denoising, CT metal artifact reduction, and OCT speckle reduction.

    Before starting my doctoral study, I worked as a Software Engineer at Huawei Cloud Computing Technology Co., Ltd., where I gained practical experience in cloud computing, large-scale distributed systems, and data analysis.

    For collaboration, feel free to reach me at yqhuang2912@gmail.com.

    News
    2026
    Our paper LLM-Orchestrated Diagnose-Plan-Treat for Mixed-Degradation CT Reconstruction was accepted to IJCAI 2026.
    Apr 30
    Our paper FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis was accepted as a regular paper at ICML 2026.
    Apr 30
    My paper Beyond Class Boundaries: Federated Visual Primitive Sharing with Text-Guided Adaptation was accepted as an oral paper at WWW 2026.
    Apr 01
    2025
    Our paper SMART: Self-supervised Learning for Metal Artifact Reduction in Computed Tomography was published in IEEE Transactions on Medical Imaging.
    Oct 06
    My paper FedRIR: Rethinking Information Representation in Federated Learning was accepted as an oral presentation at WWW 2025 (CCF-A).
    Jan 20
    2024
    Started my Ph.D. journey at Sichuan University in the School of Cyber Science and Engineering.
    Sep 10
    Publication Highlights
    *equal contribution, †corresponding author
    • IJCAI'26
      LLM-Orchestrated Diagnose-Plan-Treat for Mixed-Degradation CT Reconstruction
      Huang, Y., Chen, Y., Xu, F., Wang, T., Xia, W., Shan, H., Zhang, Y.
      International Joint Conference on Artificial Intelligence (IJCAI), Accepted, 2026.

      Accepted to IJCAI 2026. The work explores an LLM-orchestrated diagnose-plan-treat framework for mixed-degradation CT reconstruction.

    • ICML'26
      FACT: Fuzzy Alignment with Comorbidity Topology for Reliable Multi-Label Medical Image Diagnosis
      Chen, Y., Huang, Y., Qin, Y., Yang, Z., Yuan, L., Ran, M., Zhang, Y.
      International Conference on Machine Learning (ICML), Regular Paper, 2026.

      Accepted as an ICML 2026 regular paper. The work studies reliable multi-label medical image diagnosis through fuzzy alignment with comorbidity topology.

    • WWW'26
      Beyond Class Boundaries: Federated Visual Primitive Sharing with Text-Guided Adaptation
      Huang, Y., Chen, Y., Wang, T., Lu, Z., Shao, Z., Li, B., Zhang, Y.
      Proceedings of the ACM Web Conference 2026, pp. 5275-5285 (CCF-A, Oral Presentation), 2026. [Scholar]

      Studies federated visual primitive sharing with text-guided adaptation, aiming to improve visual learning beyond fixed class boundaries in distributed settings.

    • WWW'25
      FedRIR: Rethinking Information Representation in Federated Learning
      Huang, Y., Shao, Z., Yang, Z., Lu, Z., Zhang, Y.
      Proceedings of the ACM on Web Conference 2025, pp. 807-816 (CCF-A, Oral Presentation), Sydney, NSW, Australia., 2025. [Paper][Code]

      Rethinks how information is represented and exchanged in federated learning, aiming to improve collaborative training under distributed data settings.

    • TMI'20
      Noise-powered disentangled representation for unsupervised speckle reduction of optical coherence tomography images
      Huang, Y., Xia, W., Lu, Z., Liu, Y., Chen, H., Zhou, J., Fang, L., Zhang, Y.
      IEEE Transactions on Medical Imaging, 40(10), pp. 2600-2614, 2020. [Paper][Code]

      Proposes a noise-powered disentangled representation method for unsupervised speckle reduction in optical coherence tomography images.

    • OE'19
      Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network
      Huang, Y., Lu, Z., Shao, Z., Ran, M., Zhou, J., Fang, L., Zhang, Y.
      Optics Express, 27(9), pp. 12289-12307, 2019. [Paper][Code]

      Uses a generative adversarial network to perform simultaneous denoising and super-resolution for optical coherence tomography images.

    All Publications