Education

• Computer Science and Engineering, Wangxuan Institute of Computer Technology, Peking University, 2023 – Now
• Control Science and Engineering, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, 2020 – 2023
• Automation, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, 2016 – 2020

Awards and Honors

• China National Scholarship (国家奖学金), 2024
• China National Scholarship (王选计算机研究所优秀学生), 2024
• Merit Student of Peking University (北京大学三好学生), 2024
• Academic Star Nomination Award from School of Intelligence and Technology, Peking University (北京大学智能学院学术智星提名奖), 2024
• Hongcai Scholarship of Peking University (北京大学闳材奖学金), 2023

Research Interests

• Lifelong Learning, Federal Continual Learning, Label Noise Learning, Semi-Supervised Learning, Person Re-identification

Publications

1. Five papers in submission

2. Chenyu Zhang#, Kunlun Xu#, Zichen Liu, Yuxin Peng, and Jiahuan Zhou*, "SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting", in 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'25), Nashville TN, USA, Jun.11 - Jun.15, 2025

3. Zichen Liu, Kunlun Xu, Bing Su, Xu Zou, Yuxin Peng, and Jiahuan Zhou*, "STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding", in 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'25), Nashville TN, USA, Jun.11 - Jun.15, 2025

4. Kunlun Xu, Chenghao Jiang, Peixi Xiong, Yuxin Peng, and Jiahuan Zhou*, "DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification", in 39th Annual AAAI Conference on Artificial Intelligence (AAAI'25), Philadelphia, Pennsylvania, USA, Feb.25 - Mar.4, 2025.

5. Kunlun Xu, Haozhuo Zhang, Yu Li, Yuxin Peng, and Jiahuan Zhou*, "Mitigate Catastrophic Remembering via Continual Knowledge Purification for Noisy Lifelong Person Re-Identification", in 32nd ACM Multimedia Conference (ACM MM'24), Melbourne, Australia, 2024.

6. Qiwei Li, Kunlun Xu, Yuxin Peng, and Jiahuan Zhou*, "Exemplar-Free Lifelong Person Re-Identification via Prompt-guided Adaptive Knowledge Consolidation", in International Journal of Computer Vision (IJCV), 2024, pp. 1-16, Doi: 10.1007/s11263-024-02110-x

7. Kunlun Xu, Xu Zou, Yuxin Peng, and Jiahuan Zhou*, "Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification", in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'24), Seattle WA, USA, 2024, pp. 16604-16613

8. Kunlun Xu, Xu Zou, and Jiahuan Zhou*, "LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-Identification", AAAI Conf. on Artificial Intelligence (AAAI'24)

9. Kunlun Xu, Yuxin Peng, and Jiahuan Zhou*, "Uncover the Body: Occluded Person Re-identification via Masked Image Modeling", in 12rd International Conference on Image and Graphics(ICIG'23), Nanjing, China, Sep.22 - 24, 2023, pp. 241-253, Doi: 10.1007/978-3-031-46305-1_20

10. Leizhen Dong, Zhimin Li, Kunlun Xu, Zhijun Zhang, Luxin Yan, Sheng Zhong, and Xu Zou*; "Category-Aware Transformer Network for Better Human-Object Interaction Detection", in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'22), New Orleans, LA, USA, 2022, pp. 19538-19547

11. Kunlun Xu, Zhimin Li, Zhijun Zhang, Leizhen Dong, Wenhui Xu, Luxin Yan, Sheng Zhong, and Xu Zou*, "Effective Actor-centric Human-object Interaction Detection", in Image and Vision Computing (IVC'22), 2022, pp. 104422, Doi: 10.1016/j.imavis.2022.104422

Note: * indicates the corresponding author; # indicates equal contribution.

Academic Service

• International Conference on Machine Learning (ICML)

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

• Conference on Neural Information Processing Systems (NeurIPS)

• The AAAI Conference on Artificial Intelligence (AAAI)

• ACM International Conference on Multimedia (ACM MM)

• IEEE Trans on Image Processing (IEEE TIP), 2025-present

• IEEE Trans on Multimedia (IEEE TMM), 2024-present

• Pattern Recognition Letters (PRL), 2023-present