Haiyu Wang

王海宇

prof_pic.jpg
New York, NY

I am a Ph.D. student in Electrical and Computer Engineering at New York University since August 2024, advised by Prof. Sai Qian Zhang. I began my doctoral studies in August 2024. Prior to that, I received my B.S. from Peking University, where I was fortunate to be advised by Prof. Yufei Ma. I also had the pleasure of working as a research intern at the Computer Systems Laboratory at Cornell University, under the supervision of Prof. Zhiru Zhang.

My research interests lie in Machine Learning, Efficient AI/ML, Computer Architecture, Software/Hardware Co-design, and Virtual/Augmented Reality (VR/AR).

news

Mar 27, 2026 One first-author paper ECHO has been accepted to ISCA 2026!
Jan 25, 2026 One first-author paper WSVD has been accepted to ICLR 2026!
Oct 25, 2025 One paper has been accepted to ASPLOS 2026!
Sep 18, 2025 My co-first-author paper QSVD has been accepted to NeurIPS 2025 as a Spotlight paper! (Acceptance Rate: 3.5%) :tada:
Apr 12, 2025 One paper A3FR has been accepted to ICS 2025!
Mar 22, 2025 My first first-author paper POLO has been accepted to ISCA 2025! :tada:
Huge thanks to all my amazing collaborators! I’m incredibly honored to share this milestone in my research journey.

selected publications

  1. ISCA
    echo.png
    ECHO: Efficient Head-Orientation-Guided Real-Time Sound Spatialization for Virtual Reality
    Haiyu Wang, Tianhua Xia, and Sai Qian Zhang
    In Proceedings of the 53rd Annual International Symposium on Computer Architecture, 2026
  2. ICLR
    wsvd.png
    WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models
    Haiyu Wang, Yutong Wang, Jack Jiang, and Sai Qian Zhang
    In The Fourteenth International Conference on Learning Representations, 2026
    Website
  3. ASPLOS
    solo.png
    Segment Only Where You Look: Leveraging Human Gaze Behavior for Efficient Computer Vision Applications in Augmented Reality
    Tianhua Xia, Haiyu Wang, and Sai Qian Zhang
    In Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2026
    HTML
  4. NeurIPS
    qsvd.png
    QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
    Yutong Wang*, Haiyu Wang*, and Sai Qian Zhang
    In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
    Spotlight. * indicates equal contribution
    arXiv PDF Website
  5. ISCA
    polo.png
    Process Only Where You Look: Hardware and Algorithm Co-optimization for Efficient Gaze-Tracked Foveated Rendering in Virtual Reality
    Haiyu Wang, Wenxuan Liu, Kenneth Chen, Qi Sun, and Sai Qian Zhang
    In Proceedings of the 52nd Annual International Symposium on Computer Architecture, 2025
    HTML
  6. ICS
    a3fr.png
    A3FR: Agile 3D Gaussian Splatting with Incremental Gaze Tracked Foveated Rendering in Virtual Reality
    Shuo Xin, Haiyu Wang, and Sai Qian Zhang
    In Proceedings of the 39th ACM International Conference on Supercomputing, 2025
    HTML