avatar

Hanbin Zhao

Assistant Professor
Zhejiang University
zhaohanbin@zju.edu.cn


Short Bio

I am an Assistant Professor (2023-) in the College of Computer Science and the Institute of Advanced Technology at Zhejiang University. Prior to that, I got the bachelor of engineering degree (2014-2018) from the CS department of Zhejiang University, working with Prof. Hui Qian. I obtained my Ph.D degree (2018-2023) from DCD Lab@Zhejiang University, under the supervision of Prof. Xi Li.

My research interests include machine learning and computer vision, currently focusing on continual learning, machine unlearning, and generative models.

I am actively seeking highly motivated Ph.D/Master candidates who share my research interests. Kindly reach out to me at zhaohanbin@zju.edu.cn with your resume!

News

[January 2026] Our paper is accepted to ICLR 2026.
[January 2026] Our paper is accepted to TOMM.
[December 2025] Our paper about incremental learning is accepted to TIP.
[November 2025] Two papers are accepted to AAAI 2026.
[July 2025] Our paper about incremental learning is accepted to TOMM.
[June 2025] Our paper about incremental learning is accepted to JIG 2025.
[June 2025] Three papers are accepted to ICCV 2025.
[May 2025] Our paper about incremental learning is accepted to TCSVT.
[May 2025] Our paper about diffusion models is accepted to ICML 2025.
[April 2025] Two papers are accepted to IJCAI 2025.

Publications

  1. ICLR
    Equilibrium Language Models
    Yikun Jiang, Huanyu Wang, Tianhong Ding, Wenhu Zhang, Yiming Wu, Hanbin Zhao, John C.S. Lui
    The Fourteenth International Conference on Learning Representations (ICLR), 2026.
    PDF Code

  2. TOMM
    Hyperbolic Active Learning for Label-Efficient Action Segmentation
    Jingqiao Xiu, Wei Ji, Menglin Yang, Yufeng Chen, Hanbin Zhao, Fangfang Wang, Roger Zimmermann
    ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2026.
    PDF Code

  3. TIP
    IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting
    Hao Fu, Hanbin Zhao, Jiahua Dong, Henghui Ding, Chao Zhang, Hui Qian ( Corresponding authors)
    IEEE Transactions on Image Processing (TIP), 2026.
    PDF Code

  4. AAAI
    Bring Your Dreams to Life: Continual Text-to-Video Customization
    Jiahua Dong, Xudong Wang, Wenqi Liang, Zongyan Han, Meng Cao, Duzhen Zhang, Hanbin Zhao, Zhi Han, Salman Khan, Fahad Shahbaz Khan
    The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
    PDF Code

  5. AAAI
    Mass Concept Erasure in Diffusion Models with Concept Hierarchy
    Jiahang Tu, Ye Li, Yiming Wu, Hanbin Zhao, Chao Zhang, Hui Qian ( Corresponding authors)
    The 40th Annual AAAI Conference on Artificial Intelligence (AAAI), 2026.
    PDF Code

  6. TOMM
    Visuo-Tactile Class-Incremental Learning
    Hao Fu, Fengyu Yang, Wei Ji, Hanbin Zhao, Boyang Wang, Chao Zhang, Roger Zimmermann, Hui Qian ( Corresponding authors)
    ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2025.
    PDF Code

  7. JIG
    Advances in Incremental Learning Research
    Hao Fu, Qian Feng, Jiahang Tu, Hanbin Zhao, Chao Zhang, Xin Du, Hui Qian ( Corresponding authors)
    Journal of Image and Graphics (JIG), 2025.
    PDF Code

  8. ICCV
    FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
    Qian Feng, Jiahang Tu, Mintong Kang, Hanbin Zhao, Chao Zhang, Hui Qian ( Corresponding authors)
    International Conference on Computer Vision (ICCV), 2025.
    PDF Code

  9. ICCV
    Hierarchical Visual Prompt Learning for Continual Video Instance Segmentation
    Jiahua Dong, Hui Yin, Wenqi Liang, Hanbin Zhao, Henghui Ding, Nicu Sebe, Salman Khan, Fahad Shahbaz Khan
    International Conference on Computer Vision (ICCV), 2025.
    PDF Code

  10. ICCV
    Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin
    Fangyikang Wang, Hubery Yin, Lei Qian, Yinan Li, Shaobin Zhuang, Huminhao Zhu, Zhang Yilin, Yanlong Tang, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li
    International Conference on Computer Vision (ICCV), 2025.
    PDF Code

  11. TCSVT
    PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer
    Qian Feng, Hanbin Zhao, Chao Zhang, Jiahua Dong, Henghui Ding, Yu-Gang Jiang, Hui Qian ( Corresponding authors)
    IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
    PDF Code

  12. ICML
    Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
    Fangyikang Wang, Hubery Yin, Shaobin Zhuang, Huminhao Zhu, Yinan Li, Lei Qian, Chao Zhang, Hanbin Zhao, Hui Qian, Chen Li
    International Conference on Machine Learning (ICML), 2025.
    PDF Code

  13. IJCAI
    A Timestep-Adaptive Frequency-Enhancement Framework for Diffusion-based Image Super-Resolution
    Yueying Li, Hanbin Zhao, Jiaqing Zhou, Guozhi Xu, Tianlei Hu, Gang Chen, Haobo Wang
    International Joint Conference on Artificial Intelligence (IJCAI), 2025.
    PDF Code

  14. IJCAI
    Few-Shot Incremental Multi-modal Learning via Touch Guidance and Imaginary Vision Synthesis
    Lina Wei, Yuhang Ma, Zhongsheng Lin, Fangfang Wang, Canghong Jin, Hanbin Zhao, Dapeng Chen
    International Joint Conference on Artificial Intelligence (IJCAI), 2025.
    PDF Code

  15. AAAI
    Mos: Model Surgery for Pre-trained Model-based Class-incremental Learning
    Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye
    The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025.
    PDF Code

  16. AAAI
    Texttoucher: Fine-grained Text-to-Touch Generation
    Jiahang Tu, Hao Fu, Fengyu Yang, Hanbin Zhao, Chao Zhang, Hui Qian ( Corresponding authors)
    The 39th Annual AAAI Conference on Artificial Intelligence (AAAI), 2025.
    PDF Code

  17. TOMM
    DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving Data Generation
    Jiahang Tu, Wei Ji, Hanbin Zhao, Chao Zhang, Roger Zimmermann, Hui Qian ( Corresponding authors)
    ACM Transactions on Multimedia Computing, Communications and Applications (TOMM), 2025.
    PDF Code

  18. TIP
    GCSTG: Generating Class-confusion-aware Samples with a Tree-structure Graph for Few-shot Object Detection
    Longrong Yang, Hanbin Zhao, Hongliang Li, Liang Qiao, Ziwei Yang, Xi Li
    IEEE Transactions on Image Processing (TIP), 2025.
    PDF Code

  19. NeurIPS
    Belm: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
    Fangyikang Wang, Hubery Yin, Yue-Jiang Dong, Huminhao Zhu, Hanbin Zhao, Hui Qian, Chen Li
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
    PDF Code

  20. NeurIPS
    D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
    Yikun Jiang, Huanyu Wang, Lei Xie, Hanbin Zhao, Chao Zhang, Hui Qian, John CS Lui ( Corresponding authors)
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
    PDF Code

  21. NeurIPS
    Solving Zero-Sum Markov Games with Continous State via Spectral Dynamic Embedding
    Chenhao Zhou, Zebang Shen, Chao Zhang, Hanbin Zhao, Hui Qian
    Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
    PDF Code

  22. MM
    Hierarchical Debiasing and Noisy Correction for Cross-domain Video Tube Retrieval
    Jingqiao Xiu, Mengze Li, Wei Ji, Jingyuan Chen, Hanbin Zhao, Shin'ichi Satoh, Roger Zimmermann
    ACM International Conference on Multimedia (MM), 2024.
    PDF Code

  23. ECCV
    RCS-Prompt: Learning Prompt to Rearrange Class Space for Prompt-based Continual Learning
    Longrong Yang, Hanbin Zhao, Yunlong Yu, Xiaodong Zeng, Xi Li
    European Conference on Computer Vision (ECCV), 2024.
    PDF Code

  24. CVPR
    APISR: Anime Production Inspired Real-World Anime Super-Resolution
    Boyang Wang, Fengyu Yang, Xihang Yu, Chao Zhang, Hanbin Zhao ( Corresponding authors)
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    PDF Code

  25. TNNLS
    Unsupervised Domain Adaptation With Class-Aware Memory Alignment
    Hui Wang, Liangli Zheng, Hanbin Zhao, Shijian Li, Xi Li
    IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2024.
    PDF Code

  26. AAAI
    GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework
    Fangyikang Wang, Huminhao Zhu, Chao Zhang, Hanbin Zhao, Hui Qian
    The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.
    PDF Code

  27. Neurocomputing
    Structure-conditioned Adversarial Learning for Unsupervised Domain Adaptation
    Hui Wang, Jian Tian, Songyuan Li, Hanbin Zhao, Fei Wu, Xi Li
    Neurocomputing (Neurocomputing), 2022.
    PDF Code

  28. TNNLS
    Epoch-evolving Gaussian Process Guided Learning
    Jiabao Cui, Xuewei Li, Hanbin Zhao, Hui Wang, Bin Li, Xi Li
    IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2022.
    PDF Code

  29. MM
    Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation
    Xintian Wu, Hanbin Zhao, Liangli Zheng, Shouhong Ding, Xi Li
    ACM International Conference on Multimedia (MM), 2022.
    PDF Code

  30. ECCV
    RBC: Rectifying the Biased Context in Continual Semantic Segmentation
    Hanbin Zhao, Fengyu Yang, Xinghe Fu, Xi Li
    European Conference on Computer Vision (ECCV), 2022.
    PDF Code

  31. TNNLS
    Memory-efficient Class-Incremental Learning for Image Classification
    Hanbin Zhao, Hui Wang, Yongjian Fu, Fei Wu, Xi Li
    IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2021.
    PDF Code

  32. MM
    When Video Classification Meets Incremental Classes
    Hanbin Zhao, Xin Qin, Shihao Su, Yongjian Fu, Zibo Lin, Xi Li
    ACM International Conference on Multimedia (MM), 2021.
    PDF Code

  33. TNNLS
    Elastic Knowledge Distillation by Learning from Recollection
    Yongjian Fu, Songyuan Li, Hanbin Zhao, Wenfu Wang, Weihao Fang, Yueting Zhuang, Zhijie Pan, Xi Li
    IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2021.
    PDF Code

  34. SPL
    Progressive Class-based Expansion Learning For Image Classification
    Hui Wang, Hanbin Zhao, Xi Li
    IEEE Signal Processing Letters (SPL), 2021.
    PDF Code

  35. TPAMI
    MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning
    Hanbin Zhao, Yongjian Fu, Mintong Kang, Qi Tian, Fei Wu, Xi Li
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021.
    PDF Code

  36. Neurocomputing
    PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization
    Xin Qin, Hanbin Zhao, Guangchen Lin, Hao Zeng, Songcen Xu, Xi Li
    Neurocomputing (Neurocomputing), 2021.
    PDF Code

  37. TNNLS
    What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
    Hanbin Zhao, Hao Zeng, Xin Qin, Yongjian Fu, Hui Wang, Bourahla Omar, Xi Li
    IEEE Transactions on Neural Network and Learning Systems (TNNLS), 2021.
    PDF Code

  38. IJCAI
    Progressive Blockwise Knowledge Distillation for Neural Network Acceleration
    Hui Wang*, Hanbin Zhao*, Xi Li, Xu Tan (* Equal contribution)
    International Joint Conference on Artificial Intelligence (IJCAI), 2018.
    PDF Code

Professional Services

Conference Reviewers

Journal Reviewers


Powered by Jekyll and Minimal Light theme.