publications

2026

1. ICLR

   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
2. ASPLOS

   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

   To appear

2025

1. NeurIPS

   

   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 paper. *Equal contribution

   PDF Website
2. ISCA

   

   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
3. ICS

   

   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
4. Hardware and Algorithm Codesign for Efficient Gaze Tracking in Virtual Reality System

   Haiyu Wang, Wenxuan Liu, and Sai Qian Zhang

   In 2025 26th International Symposium on Quality Electronic Design (ISQED), 2025