Fan Lyu

hero image
  • Fan Lyu, PhD, Postdoc AI researcher

  • New Laboratory of Pattern Recognition (NLPR)

  • Institute of Automation, Chinese Academy of Sciences (CASIA)

  • Contact

    : fan.lyu@cripac.ia.ac.cn, fanlyu@ieee.org

I am currently a Postdoctoral Research Fellow in the New Laboratory of Pattern Recognition (NLPR) at the Institute of Automation, Chinese Academy of Sciences (CASIA), under the supervision of Prof. Liang Wang. I completed my PhD at the College of Intelligence and Computing, Tianjin University (TJU), where I was advised by Prof. Wei Feng. Prior to that, I graduated with a master’s degree from Suzhou University of Science and Technology in 2018, under the guidance of Prof. Fuyuan Hu. My research primarily focuses on Open-World Learning, including Continual Learning and Test-Time Learning. My main interest lies in developing machine learning models that can adapt effectively to dynamic environments. Additionally, I have a strong background in computer vision and multi-modal learning, with several publications in these areas. I have undertaken and participated in several research projects and am skilled at guiding teams to complete complex projects and research tasks.

🔔 I will complete my postdoctoral research in the second half of 2025 and am currently seeking related research positions.

🔔 I am currently recruiting online undergraduate interns to explore long-term artificial intelligence in open-world scenarios. I welcome passionate and inquisitive students with a strong research interest, an exploratory mindset, and unwavering perseverance to reach out. Additionally, I am open to remote collaborations with master’s and PhD students.

🔔 News


  • ‼️ 2025.03 | 1 paper was accepted by ICME 2025: Controllable Continual Test-Time Adaptation. [arxiv] [code]
  • ‼️ 2025.02 | 3 paper was accepted by CVPR 2025:
    • Maintaining Consistent Inter-Class Topology in Continual Test-Time Adaptation
    • Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation
    • Dual Semantic Guidance for Open Vocabulary Semantic Segmentation
  • ‼️ 2025.02 | 1 survey was accepted by JIG 2025: A Comprehensive Survey on Continual Learning. [paper]
  • ‼️ 2025.02 | Our book of continual learning is published: Continual Artificial Intelligence towards Changing Environment.
  • 2025.01 | 1 paper was accepted by AAAI 2025: Rebalancing Multi-Label Class-Incremental Learning.
  • 2024.07 | 1 paper was accepted by ECCV 2024: Confidence Self-Calibration for Multi-Label Class-Incremental Learning. [pdf] [code]
  • 2024.06 | 1 paper was accepted by IEEE TCSVT 2024: Overcoming Modality Bias in Question-Driven Sign Language Video Translation. [pdf] [code]
  • 2024.05 | 1 paper was accepted by IEEE TIV 2024: Dynamic V2X Perception from Road-to-Vehicle Vision. [pdf] [code]
  • 2024.01 | 1 paper was accepted by AAAI 2024 (Oral): Long-Tailed Learning as Multi-Objective Optimization. [pdf] [code]

📡 Research Interest


  • Open-World AI: Developing AI that maintains effectiveness in dynamic and ever-changing environments
  • Sustaintable AI: Ensuring AI systems remain effective and adaptive over the long term

🏹 Research Projects


  • National Science Foundation of China (NSFC), 2024~2027. (62406323)
  • China Postdoctoral Science Foundation (CPSF), 2024~2026. (2024M753496)
  • Postdoctoral Fellowship Program of CPSF, 2023~2025. (GZC20232993)

📚 Books


Continual Artificial Intelligence towards Changing Environment

面向变化场景的连续人工智能

Buy Now


Site visit: