Wang, Haiyu

3 publications

ICLR 2026 WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models Haiyu Wang, Yutong Wang, Jack Jiang, Sai Qian Zhang

NeurIPS 2025 Prompt Tuning Transformers for Data Memorization Haiyu Wang, Yuanyuan Lin

NeurIPS 2025 QSVD: Efficient Low-Rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models Yutong Wang, Haiyu Wang, Sai Qian Zhang