About

Hi, I’m Songyue Cai (蔡松岳). I am currently a second-year M.S. student in Computer Science and Technology at the University of Electronic Science and Technology of China (UESTC), where I am advised by Prof. Xiaofeng Zhu. My research interests include few-shot learning, out-of-distribution detection, and vision-language models.

🔥 News

  • 2025.04: 🎉🎉 Three papers are accepted by IJCAI 2025.
  • 2024.10: 🎉🎉 One paper is accepted by Medical Image Analysis (MIA).

📝 Publications

* indicates equal contribution, † indicates the corresponding author.

  • MCD-CLIP: Multi-view Chest Disease Diagnosis with Disentangled CLIP.
    IJCAI 2025. Paper Code
    Songyue Cai, Yujie Mo, Liang Peng, Yucheng Xie, Tao Tong, Xiaofeng Zhu

  • Background Prompt for Few-Shot Out-of-Distribution Detection. arXiv. Paper Code
    Songyue Cai, Yujie Mo, Liang Peng, Ping Hu, Xiaoshuang Shi, Xiaofeng Zhu

  • MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning. MIA 2024. Paper
    Liang Peng, Songyue Cai, Zongqian Wu, Huifang Shang, Xiaofeng Zhu, Xiaoxiao Li

  • Seeking Proxy Point via Stable Feature Space for Noisy Correspondence Learning. IJCAI 2025. Paper
    Yucheng Xie, Songyue Cai, Tao Tong, Ping Hu, Xiaofeng Zhu

  • Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background. arXiv. Paper
    Tianyu Li, Songyue Cai, Zongqian Wu, Ping Hu, Xiaofeng Zhu

  • Meta Label Correction with Generalization Regularizer. IJCAI 2025. Paper
    Tao Tong, Yujie Mo, Yuchen Xie, Songyue Cai, Xiaoshuang Shi, Xiaofeng Zhu

🎖 Honors and Awards

  • 2025.10 Outstanding Graduate Student
  • 2025.10 First-class Scholarship
  • 2024.10 First-class Scholarship
  • 2020.10 First-class Scholarship

📖 Education

  • 2024.09 - Present, University of Electronic Science and Technology of China, Chengdu, China
    M.S. in Computer Science and Technology

  • 2020.09 - 2024.06, Chongqing University, Chongqing, China
    B.S. in Information Security

💬 Services

Conference

  • Reviewer: AAAI Conference on Artificial Intelligence (AAAI), 2027.