About Me

I am currently a Postdoctoral Research Fellow in the Department of Computing at The Hong Kong Polytechnic University, working with Prof. Changwen Chen. I received my B.E. and M.E. degrees in Instrumentation and Optoelectronic Engineering from Beihang University in 2016 and 2019, respectively, and my Ph.D. in Computer Science and Technology from Harbin Institute of Technology (Shenzhen) in 2026, supervised by Prof. Min Zhang and Prof. Liqiang Nie. During my doctoral studies, I also worked closely with Prof. Jianlong Wu and Prof. Yue Yu. Before pursuing my Ph.D., I worked at SenseTime from 2019 to 2022, where I conducted computer vision research and served as a Research Manager. My work has been published in leading international conferences and journals, including IEEE TPAMI, CVPR, NeurIPS, ICML, ECCV, and ACM Multimedia. I have served as a reviewer for leading journals and conferences in computer vision and machine learning. My research interests include embodied intelligence and multimodal learning, with a particular focus on vision-language navigation and continual learning.

News

• 2026.08I was invited to serve as a Senior Area Chair for COLING 2027.
• 2026.07Mamba-FSCIL was accepted to IEEE TPAMI.
• 2026.07Two papers were accepted to ACM Multimedia 2026.
• 2026.07I joined The Hong Kong Polytechnic University as a Postdoctoral Research Fellow.
• 2025One paper was accepted to CVPR 2025.
• 2024Our work was accepted to NeurIPS, ECCV, and ICML 2024.
• 2023Two first-author papers were accepted to ACM Multimedia 2023.

Selected Publications

^* Equal contribution   ^† Corresponding author

1. Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning

   Xiaojie Li, Yibo Yang, Jianlong Wu^†, Yue Yu, Ming-Hsuan Yang, Liqiang Nie, Min Zhang. IEEE TPAMI, 2026. [Code]

2. Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning

   Xiaojie Li, Wei Liu, Bei Wang, Jianlong Wu^†, Yue Yu, Min Zhang. ACM MM, 2026. [Code]

3. AirForesight: Current-to-Future Spatial Map Imagination with Cross-Space Planning Consistency for UAV-VLN

   Yutong Liu^*, Xiaojie Li^*†, Mingzhu Xu, Jianlong Wu^†. ACM MM, 2026.

4. Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization

   Sihao Liu, Yibo Yang^†, Xiaojie Li, David A. Clifton, Bernard Ghanem. CVPR, 2025.

5. CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning

   Yibo Yang, Xiaojie Li, Zhongzhu Zhou, Shuaiwen Leon Song, Jianlong Wu, Liqiang Nie^†, Bernard Ghanem^†. NeurIPS, 2024. [Code]

6. GenView: Enhancing View Quality with a Pretrained Generative Model for Self-Supervised Learning

   Xiaojie Li, Yibo Yang^†, Xiangtai Li, Jianlong Wu^†, Yue Yu, Bernard Ghanem, Min Zhang. ECCV, 2024. [Code]

7. Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation

   Yibo Yang, Xiaojie Li, Motasem Alfarra, Hasan Hammoud, Adel Bibi, Philip Torr, Bernard Ghanem. ICML, 2024.

8. Fine-grained Key-Value Memory Enhanced Predictor for Video Representation Learning

   Xiaojie Li, Jianlong Wu^†, Shaowei He, Shuo Kang, Yue Yu, Liqiang Nie, Min Zhang. ACM MM, 2023. [Code]

9. Mask Again: Masked Knowledge Distillation for Masked Video Modeling

   Xiaojie Li, Shaowei He, Jianlong Wu^†, Yue Yu, Liqiang Nie^†, Min Zhang. ACM MM, 2023. [Code]

10. HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

    Luting Wang, Xiaojie Li, Yue Liao^†, Zeren Jiang, Jianlong Wu, Fei Wang, Chen Qian, Si Liu. ECCV, 2022. [Code]

11. Local Correlation Consistency for Knowledge Distillation

    Xiaojie Li, Jianlong Wu^†, Hongyu Fang, Yue Liao, Fei Wang, Chen Qian. ECCV, 2020.

12. Agree to Disagree: Adaptive Ensemble Knowledge Distillation in Gradient Space

    Shangchen Du^*, Shan You^*†, Xiaojie Li, Jianlong Wu^†, Fei Wang, Chen Qian, Changshui Zhang. NeurIPS, 2020.

13. Detector-in-Detector: Multi-level Analysis for Human-Parts

    Xiaojie Li, Lu Yang, Qing Song, Fuqiang Zhou. ACCV, 2018.

14. High-Frequency Details Enhancing DenseNet for Super-Resolution

    Fuqiang Zhou, Xiaojie Li, Zuoxin Li. Neurocomputing, 2018.

Honors & Awards

• 2026 2nd Place, Unlearnable Videos Competition, LifeGenIP Workshop at ECCV 2026.
• 2025 1st Place, Composed Video Retrieval Challenge, CVPR 2025 VidLLMs Workshop; established a new state of the art in Recall@K.
• 2019 Excellent Graduate of Beijing.
• 2019 Excellent Graduate Thesis of Beihang University.

Education & Experience

• 2026–Present Postdoctoral Research Fellow, Department of Computing, The Hong Kong Polytechnic University, Hong Kong.
• 2022–2026 Ph.D. in Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen.
• 2019–2022 Research Manager, SenseTime, Beijing.
• 2016–2019 M.E. in Instrumentation and Optoelectronic Engineering, Beihang University, Beijing.
• 2012–2016 B.E. in Instrumentation and Optoelectronic Engineering, Beihang University, Beijing.

Academic Service

Journal reviewer: TPAMI, IJCV, TNNLS, TMM, TKDE, and Pattern Recognition.

Conference reviewer: NeurIPS, CVPR, ICCV, ICML, ACM Multimedia, and ICLR.