Zhiyuan Yan
📖 PhD Student, 2024.09-2028.07(expected)
🏫 Peking University, previously at CUHK-SZ
💡 Multimodal, AIGC Detection, AIGC, AI4Science
Email / Github / Scholar / OpenReview
About Me
  • I am a second-year CS PhD Student at Peking University (PKU), supervised by Prof. Li Yuan and Prof. Fanyang Mo.
  • I have published 10+ CCF-A papers (as the first/co-first author) with a total Google Scholar citations of 1000+, including an oral paper at ICML 2025 (top 1%).
  • I am/was previously a research intern in LongCat Foundation Model Team, Baidu ERNIE Star Program, Tencent Youtu Lab, Tencent AILab, and DJI.
  • My research interests cover: Multimodal, LLM, AIGC, AI Safety, AI4Science.
    • Research Highlights (🧑‍💻 Co-first Author, 📮 Corresponding Author)
    See Google Scholar for my full publication list.
    Unified Multimodal Model as Auto-Encoder
    Zhiyuan Yan, et al.
    CVPR, 2026
    arXiv / Project Page
    Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
    Zhiyuan Yan, et al.
    ICML, Oral 🏆, 2025
    arXiv / Project Page
    GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
    Zhiyuan Yan, et al.
    Tech Report, 2025
    arXiv / Project Page
    ImgEdit: A Unified Image Editing Dataset and Benchmark
    Yang Ye 🧑‍💻, et al., Zhiyuan Yan 🧑‍💻
    NeurIPS, 2025
    arXiv / Project Page
    Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding
    Liuzhenghao Lv, et al., Zhiyuan Yan
    Nature Communication (reviewed), 2024
    arXiv / Project Page
    DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
    Zhiyuan Yan, et al.
    NeurIPS, 2023
    arXiv / Project Page