Xiangyan Liu

School of Computing, National University of Singapore

Hello! I’m Xiangyan, a second-year PhD student in Computer Science at National University of Singapore, where I’m fortunate to be advised by Prof. Michael Qizhe Shieh. My research centers on multimodal and agentic foundation models, with an interest in solutions that are simple, generalizable, and scalable.

Prior to my PhD, I gained valuable industry experience through internships at Shanghai AI Lab and Alibaba Tongyi. I also had the invaluable opportunity to work with Prof. Tao Lin at Westlake University, whose mentorship deeply inspired me and shaped my path to research. Recently, I’m fortunate to be working closely with Dr. Tianyu Pang, Dr. Chao Du and Dr. Longxu Dou at Sea AI Lab.

Feel free to reach out if you would like to chat or discuss any ideas! You can find my contact information at the bottom of this page.

selected works

  1. Preprint
    MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
    Zijian Wu*, Xiangyan Liu*, Xinyuan Zhang*, Lingjun Chen*, Fanqing Meng*, Lingxiao Du*, Yiran Zhao*, Fanshi Zhang*, Yaoqi Ye, Jiawei Wang, and 5 more authors
    arXiv preprint arXiv:2509.24002, 2025
    arXiv Code
  2. NeurIPS 2025
    NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
    Xiangyan Liu*, Jinjie Ni*, Zijian Wu*, Chao Du, Longxu Dou, Haonan Wang, Tianyu Pang, and Michael Qizhe Shieh
    In Advances in Neural Information Processing Systems (NeurIPS), 2025, 2025
    arXiv Code
  3. NAACL 2025
    CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases
    Xiangyan Liu*, Bo Lan*, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Fei Wang, Michael Shieh, and Wenmeng Zhou
    In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics, 2025
    arXiv Code
  4. ICLR 2024
    Towards Robust Multi-Modal Reasoning via Model Selection
    Xiangyan Liu*, Rongxue Li*, Wei Ji, and Tao Lin
    In The Twelfth International Conference on Learning Representations, 2024
    arXiv Code
  5. MM 2023 (Oral)
    Online Distillation-Enhanced Multi-Modal Transformer for Sequential Recommendation
    Wei Ji*, Xiangyan Liu*, An Zhang, Yinwei Wei, Yongxin Ni, and Xiang Wang
    In Proceedings of the 31st ACM International Conference on Multimedia, 2023
    arXiv Code