avatar

段思远

Siyuan Duan

M.S. Student
Sichuan University
siyuanduancn@gmail.com

Research Interests

Large Vision Language Model
Multi-modal Learning
AI for Science (PINNs)


Welcome to my personal homepage. I’m an incoming Ph.D student at the Department of Computer Science and Engineering (CSE), HKUST Logo The Hong Kong University of Science and Technology (HKUST). I will conduct my doctoral studies under the supervision of Prof. Hao Chen. Previously, I gained valuable experience as a research intern at HKUST LogoAlibaba Group.

🌟 I’m currently concentrating on research in the Large Vision Language Model (LVLM). If you are interested in collaborating with me or want to have a chat, please feel free to contact me via email !

News

  • [01/2026] I start my intern at Alibaba group.
  • [10/2025] I got a PhD offer from HKUST CSE.
  • [07/2025] I gave a talk at the AI TIME pre-talk and introduced our FUML (ICML'25). You can see here.
  • [05/2025] Amazing! 2 papers were accepted to ICML 2025! One was accepted as Spotlight (acc rate = 2.6%)! Thanks to all coauthors. 🎉
  • [02/2025] 1 paper was accepted to CVPR 2025(acc rate = 22.1%)! Thanks to all coauthors. 🎉
  • [09/2024] 1 paper was accepted to Neural Networks. Thanks to all coauthors. 🎉

Selected Publications

/Preprint/

Robust Fuzzy Multi-view Learning under View Conflict, Siyuan Duan, Yuan Sun, Dezhong Peng, Yingke Chen, Xi Peng, Peng Hu#, arXiv'2026. (Submitted to TPAMI)

/Publicated/

  1. Deep Fuzzy Multi-view Learning for Reliable Classification
    Siyuan Duan, Yuan Sun, Dezhong Peng, Guiduo Duan, Xi Peng, and Peng Hu#
    International Conference on Machine Learning (ICML), 2025.
    Link Code Video
  2. CoPINN: Cognitive Physics-Informed Neural Networks
    Siyuan Duan*, Wenyuan Wu*, Peng Hu, Zhenwen Ren, Dezhong Peng, and Yuan Sun#
    International Conference on Machine Learning (ICML), 2025, (Spotlight,acc rate=2.6%).
    Link Code Video
  3. Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval
    Siyuan Duan, Yuan Sun, Dezhong Peng, Zheng Liu, Xiaomin Song, and Peng Hu#
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
    Link Code Report
  4. Deep Fuzzy Physics-Informed Neural Networks for Forward and Inverse PDE Problems
    Wenyuan Wu*, Siyuan Duan*, Yuan Sun, Yang Yu, Dong Liu#, and Dezhong Peng#
    Neural Networks (NN), 2025, (IF=6.6).
    Link Code Report

“*” and “#” indicate equal contribution and the corresponding author, respectively. For full publications, please refer to my Google Scholar.

Industrial Experience

Research Intern @ Taobao&Tmall Group of Alibaba Jan. 2026 - Jul. 2026
Topic: Large Vision Language Model (LVLM).

Services

  • Conference Reviewer: NeurIPS, AAAI, ACL ARR.
  • Journal Reviewer: ACM TOIS, Neurocomputing.

Honors & Awards

  • Full Postgraduate Studentship @ HKUST (2026 - 2030)
  • China National Scholarship (2025 @ SCU, 2020 @ CAFUC)

Cutest pup, right here! dog