Photo

Harold Haodong Chen

Undergraduate
Northwestern Polytechnical University
Email: haroldchen328 [at] gmail.com

Biography

I'm a final-year undergraduate student at Northwestern Polytechnical University (NPU) and a research intern at Everlyn AI. I'm fortunate to work closely with Prof. Ser-Nam Lim from University of Central Florida (UCF) and Prof. Harry Yang from the Hong Kong University of Science and Technology (HKUST).

Previously, I was advised by Prof. Dian Shao from both NPU and Shanghai AI Laboratory, which contributed to my development in this field. I also worked with Prof. Mulin Chen and Prof. Xuelong Li from TeleAI, China Telecom, as well as Prof. Yuxuan Liang from HKUST(GZ).

As an EE major student, I have more than a passing interest in computer vision, and open to all forms of research collaboration. Feel free to contact me if you are interested in working with me! My research interests include:

News

  • [02/2025] FinePhys is accepted to CVPR'25!
  • [02/2025] Served as a reviewer for ICCV'25.
  • [02/2025] Served as a reviewer for Pattern Recognition.
  • [01/2025] Served as a reviewer for ACM TOMM.
  • [12/2024] Served as a reviewer for ICML'25.
  • [12/2024] SeFAR is accepted to AAAI'25!
  • [11/2024] Served as a reviewer for CVPR'25.
  • [10/2024] Served as a reviewer for AISTATS'25.
  • [08/2024] Served as a reviewer for ICLR'25.
  • [07/2024] FineCLIPER and CREST are accepted to MM'24!
    More
  • [05/2024] Served as a reviewer for NeurIPS'24.
  • [02/2024] Served as a reviewer for ECCV'24.
  • [01/2024] Served as a reviewer for MM'24.
  • [01/2024] UrbanCLIP is accepted to WWW'24!

    • Experience

    Research Intern | Everlyn AI
    Time: 7/2024 - 3/2025. Mentor: Prof. Ser-Nam Lim

    Research Intern | HKGAI
    Time: 5/2024 - 8/2024. Mentor: Prof. Wenhan Luo

    Research Intern | DianLab, NPU
    Time: 6/2023 - 8/2024. Advisor: Prof. Dian Shao

    Preprints

    Temporal Regularization Makes Your Video Generator Stronger
    Harold Haodong Chen, Haojian Huang, Xianfeng Wu, Yexin Liu, Yajing Bai, Wen-Jie Shu, Harry Yang, Ser-Nam Lim†
    arXiv, 2025
    [arXiv] [Webpage]

    LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
    Xianfeng Wu*, Yajing Bai*, Haoze Zheng*, Harold Haodong Chen* (co-first), Yexin Liu*, Zihao Wang, Xuran Ma, Wen-Jie Shu, Harry Yang, Ser-Nam Lim†
    arXiv, 2025
    [arXiv] [Code]

    Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning
    Harold Haodong Chen, Harry Yang, Ser-Nam Lim†
    arXiv, 2024
    [arXiv] [Webpage] [Benchmark]

    Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding
    Kaijing Ma*, Haojian Huang*, Jin Chen*, Haodong Chen, Pengliang Ji, Xianghao Zang, Han Fang, Chao Ban, Hao Sun, Mulin Chen†, Xuelong Li†
    arXiv, 2024
    [arXiv] [Webpage] [Code]

    GaussianVTON: 3D Human Virtual Try-ON via Multi-Stage Gaussian Splatting Editing with Image Prompting
    Haodong Chen, Yongle Huang, Haojian Huang, Xiangsheng Ge, Dian Shao†
    arXiv, 2024
    [arXiv] [Webpage] [Code]

    Publications

    FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
    Dian Shao†, Mingfei Shi, Shengda Xu, Haodong Chen, Yongle Huang, Binglu Wang
    IEEE/CVF Computer Vision and Pattern Recognition (CVPR), 2025
    [Paper] [arXiv] [Webpage] [Code]

    SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization
    Yongle Huang*, Haodong Chen* (co-first), Zhenbang Xu, Zihan Jia, Haozhou Sun, Dian Shao†
    AAAI Conference on Artificial Intelligence (AAAI), 2025
    [Paper] [arXiv] [Code] [Dataset]

    FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs
    Haodong Chen, Haojian Huang, Junhao Dong, Mingzhe Zheng, Dian Shao†
    ACM International Conference on Multimedia (MM), 2024
    [Paper] [arXiv] [Webpage]

    CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot Learning
    Haojian Huang, Xiaozhen Qiao, Zhuo Chen, Haodong Chen, Bingyu Li, Zhe Sun, Mulin Chen†, Xuelong Li†
    ACM International Conference on Multimedia (MM), 2024
    [Paper] [arXiv] [Code]

    UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web
    Yibo Yan, Haomin Wen, Siru Zhong, Wei Chen, Haodong Chen, Qingsong Wen, Roger Zimmermann, Yuxuan Liang†
    ACM International World Wide Web Conference (WWW), 2024
    [Paper] [arXiv] [Video] [Code]

    Awards and Honors

  • Outstanding University Student of NPU
    		•  2024
  • Innovation and Entrepreneurship Advanced Individual Honor, NPU
    		•  2024
  • School Scholarship, NPU
    		•  2024
  • University Student Innovation Fund, Ministry of Education of P.R. China
    		•  2023
  • Academic Advancement Individual Honor, NPU
    		•  2023
  • School Scholarship, NPU
    		•  2023

    Services

  • Conference Reviewer,
      Computer Vision and Pattern Recognition (CVPR), 2025
      International Conference on Computer Vision (ICCV), 2025
      European Conference on Computer Vision (ECCV), 2024
      International Conference on Machine Learning (ICML), 2025
      International Conference on Learning Representations (ICLR), 2025
      Neural Information Processing Systems (NeurIPS), 2024-2025
      ACM International Conference on Multimedia (MM), 2024
      International Conference on Artificial Intelligence and Statistics (AISTATS), 2025
  • Journal Reviewer,
      Pattern Recognition
      ACM Transactions on Multimedia Computing Communications and Applications (TOMM)