publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. On the Universal Structure in Deterministic Generative Diffusion
    arXiv preprint arXiv:2611.10338, 2026
    An earlier version of this work (April 2026), developed with minimal AI input, is available here.
  2. LEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear Leaps
    Haowei Zheng, Zhenyu Zhou, Jiawei Chen, Can Wang, and Defang Chen†
    In Proceedings of the ACM International Conference on Multimedia, 2026
  3. DecFlowEdit: Self-Localized Flow-based Image Editing via Guidance Decoupling
    Zheyuan Zhan, Can Wang, Jiawei Chen, Chun Chen, Siwei Lyu, Zeyu Zheng, and Defang Chen†
    arXiv preprint arXiv:2609.34237, 2026
  4. Spectral Amplitude Purification in Distribution Matching for Diffusion Distillation
    arXiv preprint arXiv:2609.29116, 2026
  5. Analyzing and Improving Training-Free Fast Sampling of Text-to-Image Diffusion Models
    In European Conference on Computer Vision, 2026

2025

  1. Geometric Regularity in Deterministic Sampling Dynamics of Diffusion-based Generative Models
    Journal of Statistical Mechanics: Theory and Experiment, 2025
    Top-tier journal in Statistical Mechanics. Published more than 30 papers from the Nobel Laureate Giorgio Parisi (Physics, 2021).
  2. Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges
    Qijie Xu, Can Wang, Jiawei Chen, Siwei Lyu, and Defang Chen
    arxiv, 2025
  3. DICE: Distilling Classifier-Free Guidance into Text Embeddings
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2025
    Oral, 4.7%
  4. Conditional Image Synthesis with Diffusion Models: A Survey
    Zheyuan Zhan, Defang Chen†, Jian-Ping Mei, Zhenghe Zhao, Jiawei Chen, Chun Chen, Siwei Lyu, and Can Wang
    Transactions on Machine Learning Research, 2025
  5. Knowledge distillation with refined logits
    Wujie Sun, Defang Chen†, Siwei Lyu, Genlang Chen, Chun Chen, and Can Wang
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024

  1. Simple and fast distillation of diffusion models
    In Advances in Neural Information Processing Systems, 2024
  2. On the Trajectory Regularity of ODE-based Diffusion Sampling
    In International Conference on Machine Learning, 2024
  3. Fast ODE-based Sampling for Diffusion Models in Around 5 Steps
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
  4. Knowledge Distillation on Deep Neural Networks
    Zhejiang University, Outstanding Doctoral Dissertation award (Top 2%)

2023

  1. A Geometric Perspective on Diffusion Models
    arXiv preprint arXiv:2305.19947, 2023
    The earliest work connecting Mean Shift and Diffusion Models.

2022

  1. Knowledge Distillation with the Reused Teacher Classifier
    Defang Chen, Jian-Ping Mei, Hailin Zhang, Can Wang, Yan Feng, and Chun Chen
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
  2. Confidence-aware multi-teacher knowledge distillation
    Hailin Zhang, Defang Chen, and Can Wang
    In IEEE International Conference on Acoustics, Speech and Signal Processing, 2022

2021

  1. Distilling holistic knowledge with graph neural networks
    Sheng Zhou, Yucheng Wang, Defang Chen, Jiawei Chen, Xin Wang, Can Wang, and Jiajun Bu
    In Proceedings of the IEEE/CVF international conference on computer vision, 2021
  2. Cross-Layer Distillation with Semantic Calibration
    Defang Chen, Jian-Ping Mei, Yuan Zhang, Can Wang, Zhe Wang, Yan Feng, and Chun Chen
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2021
    Journal version published in IEEE Trans. Knowl. Data Eng. (TKDE)
    Highly-Cited Paper Indexed by 2024/2025 Google Scholar Metrics

2020

  1. Online Knowledge Distillation with Diverse Peers
    Defang Chen, Jian-Ping Mei, Can Wang, Yan Feng, and Chun Chen
    In Proceedings of the AAAI Conference on Artificial Intelligence, 2020
    Highly-Cited Paper Indexed by 2024/2025 Google Scholar Metrics