Zheren Fu

PhD student

School of Cyber Science and Technology
University of Science and Technology of China

A504, Xinzhi Building, Gaoxin Campus of USTC, Hefei, China
fzr@mail.ustc.edu.cn
[Google Scholar] [Linkedin] [Github]

Biography

I'm a final year Ph.D student in University of Science and Technology of China (USTC). And I'm studying in the National Engineering Laboratory for Brain-inspired Intelligence Technology and Application (NEL-BITA) and Laboratory for Future Networks (LFN) supervised by Professor Zhendong Mao. My research field includes Artificial Intelligence, Computer Vision, Natural Language Processing, Large Multi-modal Model, and Cross-modal Alignment.

Education

  • University of Science and Technology of China, Hefei, 2020.9-2025.6
    Ph.D's Degree, Cyberspace Security

  • University of Science and Technology of China, Hefei, 2016.9-2020.6
    Bachelor's Degree, Electronic Information Engineering
    GPA: 3.81/4.3

Experiences

  • Multi-modal Algorithm Engineer (internship), 2024.5-Now
    Alibaba Group, Beijing
    I work in the Qwen Team of Tongyi Laboratory, and focus on the post-training for the Qwen-VL series.

  • Image Algorithm Engineer (internship), 2019.12-2020.10
    Kuaishou Technology, Hangzhou
    I work in the Search Technology Department, and focused on image retrieval with Prof. Lei Zhang.

  • Teaching Assistant, 2019.8-2020.1
    University of Science and Technology of China, Hefei
    I took charge of the Basic Circuit Theory for EECS undergraduate students.

Publications

First Author

  • Zheren Fu, Lei Zhang, Hou Xia, Zhendong Mao*, Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2024 [PDF] [Link] [Code]

  • Zheren Fu, Zhendong Mao*, Yan Song, Yongdong Zhang, Learning Semantic Relationship among Instances for Image-Text Matching, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, CCF-A), 2023 [PDF] [Link] [Code]

  • Zheren Fu, Zhendong Mao*, Bo Hu, Anan Liu, Yongdong Zhang, Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning, IEEE Transactions on Multimedia (T-MM, CCF-B), 2022 [PDF] [Link] [Code]

  • Zheren Fu, Zhendong Mao*, Chenggang Yan, Anan Liu, Hongtao Xie, Yongdong Zhang, Self-supervised Synthesis Ranking for Deep Metric Learning, IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT, CCF-B), 2021 [PDF] [Link]

  • Zheren Fu#, Yan Li#, Zhendong Mao*, Quan Wang, Yongdong Zhang, Deep Metric Learning with Self-Supervised Ranking, AAAI Conference on Artificial Intelligence (AAAI, CCF-A), 2021 [PDF] [Link]

Others

  • Licheng Zhang, Zhendong Mao*, Yixing Peng, Zheren Fu, Yongdong Zhang, Multi-Prototype Grouping for Continual Learning in Visual Question Answering, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP, CCF-B), 2025 [Link]

  • Qwen Team (as the Core Contributors), Qwen2.5-VL Technical Report, Arxiv, 2025.02 [Link] [Code]

  • Qwen Team (as the Contributors), Qwen2.5 Technical Report, Arxiv, 2024.12 [Link] [Code]

Honors & Awards

  • National Scholarship for Postgraduate Students, 2021

  • USTC Excellent Graduation Project, 2020

Services

  • Program Committee Member: CVPR(25, 24), ICCV(25), NeurIPS(25), AAAI(25, 24, 23), ACM-MM(25)

  • Invited Reviewer: T-PAMI, T-MM, T-CSVT

Patents

  • 毛震东，张勇东，赵博文，付哲仁，基于图像情感倾向的多模态谣言检测方法，申请号:202010940956.5

  • 张勇东，毛震东，邓旭冉，付哲仁，一种基于预训练语言模型的网络谣言检测方法，申请号:201911379298.0