Yulun Zhang

Associate Professor
Office: 5-517 Software Building, AI Institute, Shanghai Jiao Tong University
Email: yulun100@gmail.com

I have been a tenure-track associate professor at Shanghai Jiao Tong University since Mar. 2024. Previously, I was a postdoctoral researcher at Computer Vision Lab, ETH Zürich, Switzerland. I obtained my Ph.D. degree from Department of Electrical & Computer Engineering, Northeastern University, USA, in Aug. 2021. Before that I received my master degree from the Department of Automation, Tsinghua University, China, in Jul. 2017 and B.E degree from School of Electronic Engineering, Xidian University, China, in Jul. 2013. I was an intern or visiting student at Adobe Research, Harvard University, Nanyang Technological University, The University of Sydney, and Shenzhen Institute of Advanced Technology, CAS.

My research interest broadly includes machine learning and computer vision. Specifically, I focus on image/video restoration (e.g., super-resolution, denoising, deblurring), synthesis (e.g., style transfer, texture transfer), biomedical image enhancement and analysis, deep model compression (e.g., network pruning, quantization), computational imaging (e.g., spectral compressive imaging), multimodal learning, large language model, efficient diffusion model, etc. I am/was an Area Chair for CVPR’(2023-2025), ICCV’(2023,2025), ECCV’2024, NeurIPS’(2023-2025), ICLR’(2024-2025), ICML’(2024-2025), ACM MM’(2024-2025), IJCAI’(2024-2025), PRCV’2024 and Senior Program Committee (SPC) member for IJCAI’(2021-2023), AAAI’(2023-2025).

Openings: We are looking for self-motivated undergraduate interns, graduate students, and PostDocs to join our group. If you are interested, please email me with your resume and transcript. You can also refer to CSRankings for CV, ML, and AI ranking information.

大家好！欢迎本科实习生，硕士/博士，博士后加入我们，一起做有影响力的科研！有意向的同学请发送邮件给我，并附上简历和成绩单，详情如下：

点击查看申请详情

本科实习生申请

  • 基本要求：上海交大本科大一、大二、大三学生
  • 附件材料：简历+成绩单
  • 邮件题目：本科实习-姓名-学校-专业
更多关于本科实习的信息请见Openings。

硕士、博士申请

  • 基本要求：直博需获得当年所在学校的推免名额，普博需入学时获得硕士学位
  • 附件材料：简历+成绩单
  • 邮件题目：硕士申请-姓名-学校-专业，直博申请-姓名-学校-专业，普博申请-姓名-学校-专业

博后申请

  • 基本要求：入职时获得博士学位
  • 附件材料：简历
  • 邮件题目：博后申请-姓名-博士学校-专业

News

Feb 2025 I am serving as an Area Chair for NeurIPS 2025 and ACM MM 2025.
Dec 2024 I am serving as an Area Chair for ICML 2025, ICCV 2025, and IJCAI 2025.
Sep 2024 I am serving as an Area Chair for CVPR 2025 and 7 papers accepted to NeurIPS 2024.
Aug 2024 I am serving as an Area Chair for ICLR 2025.
Jul 2024 4 papers accepted to ECCV 2024.
Jun 2024 Received a gift funding from Adobe Research. I am serving as a Senior Program Committee (SPC) member for AAAI 2025.
May 2024 4 papers accepted to ICML 2024.
Mar 2024 I am serving as an Area Chair for NeurIPS 2024.
Feb 2024 5 papers accepted to CVPR 2024.
Jan 2024 I am serving as an Area Chair for ECCV 2024, ICML 2024, and PRCV 2024. 3 papers accepted to ICLR 2024.
Dec 2023 We release DPoser, a robust 3D human pose prior leveraging diffusion models (project, code, paper).
Nov 2023 I am serving as an Area Chair for ACM MM 2024 and IJCAI 2024 . We have also released several works: PromptSR (text prompt in image super-resolution), BiDRN (binarization in 3D whole-body human mesh recovery), DeqIR (parallel sampling in diffusion-based image restoration), and Reti-Diff (Retinex-based latent DM and Transformer for illumination degradation image restoration).
Sep 2023 4 papers accepted to NeurIPS 2023. Among them, HI-Diff is a diffusion model for realistic image deblurring. BiSCI is the first work about binarization in spectral compressive imaging.
Aug 2023 I am serving as an Area Chair for ICLR 2024.
Jul 2023 9 papers accepted to ICCV 2023 and 2 papers accepted to ACM MM 2023.
Jun 2023 I am serving as an Area Chair for CVPR 2024 and a Senior Program Committee (SPC) member for AAAI 2024. 1 paper about blind SR is accepted to TIP. 1 paper is accepted to MICCAI 2023. Pyramid Attention Networks for Image Restoration is accepted to IJCV.
May 2023 I am serving as an Associate Editor for Multimedia Tools and Applications (MTAP). 1 paper accepted to TIP.
Apr 2023 1 paper accepted to TPAMI and 1 paper accepted to ICML 2023. I am serving as a Reviewer for ACM MM 2023. We are also collecting papers about Diffusion Models in Low-Level Vision. Welcome to make your contributions!
Mar 2023 I am serving as an Area Chair for NeurIPS 2023 and a Reviewer for MICCAI 2023.
Feb 2023 6 papers accepted to CVPR 2023.
Jan 2023 3 papers accepted to ICLR 2023, 1 paper accepted to ISBI 2023.
Dec 2022 I am serving as a Senior Program Committee (SPC) member for IJCAI 2023 and Reviewer for ICML 2023.
Nov 2022 I am serving as an Area Chair for ICCV 2023. We have 2 papers accepted to AAAI 2023. They are about lightweight SR (HPUN) and hyperspectral image denoising (SST).
Oct 2022 I am serving as an Area Chair for CVPR 2023. We have 1 paper accepted to TIP.
Sep 2022 We have 2 papers accepted to NeurIPS 2022. They are about image restoration (CAT) and spectral compressive imaging (DAUHST).
Jul 2022 I am serving as a Senior Program Committee (SPC) member for AAAI 2023 and reviewer for ICLR 2023. We have 5 papers accepted to ECCV 2022 and 1 paper accepted to TPAMI.
Jun 2022 We have released the codebase for Spectral Compressive Imaging. We have 1 paper accepted to TPAMI and 2 papers accepted to ACM MM 2022.
May 2022 We have 2 papers accepted to ICML 2022. Our paper RCAN ranks top 10 most influential papers based on citations in ECCV 2018. See Most Influential ECCV Papers.
Apr 2022 We have 2 papers accepted to IJCAI 2022. We won the first place in NTIRE Spectral Reconstruction Challenge at CVPR, 2022. The paper and codebase of our solution MST++ have been released.
Mar 2022 We have 3 papers (two about spectral compressive imaging, one about interpretable image SR) accepted to CVPR 2022. I am serving as reviewer for ECCV 2022 and NeurIPS 2022.
Jan 2022 We have 1 paper accepted to TPAMI and another one accepted to ICLR 2022. I am serving as reviewer for ACM MM 2022 and MICCAI 2022.
Dec 2021 I am serving as SPC for IJCAI 2022 and reviewer for ICML 2022.
Sep 2021 3 papers are accepted to NeurIPS 2021. I am serving as reviewer for CVPR 2022.
Jul 2021 3 papers are accepted to ICCV 2021. I accept the invitation to the novel Program Committee Board of IJCAI with service time from 2022 to 2024.
Jun 2021 1 paper is accepted to TCYB and TIP. I am serving as reviewer for ICLR 2022.
Apr 2021 Our real-world image denoising paper is accepted to IJCAI 2021. I am serving as reviewer for NeurIPS 2021 and ACM MM 2021.
Mar 2021 Our papers about MR image enhancement and real-world image denoising are accepted to CVPR 2021. One paper about MR image super-resolution is accepted to TCSVT.
Feb 2021 Our paper RDN ranks top 10 most influential papers based on citations in CVPR 2018. See Most Influential CVPR Papers.
Jan 2021 Our Neural Pruning paper (code) is accepted to ICLR 2021. I am serving as reviewer for ICCV 2021.
Dec 2020 I am serving as a Senior Program Committee (SPC) member for IJCAI 2021 and PC member for ICML 2021, MICCAI 2021.
Sep 2020 We have 1 paper accepted to TNNLS and another one accepted to NeurIPS 2020. Code will be available soon.
Jul 2020 We have 2 papers accepted to ECCV 2020. Code/data will be available soon.
Jun 2020 We release the code for our paper: Pyramid Attention Networks for Image Restoration
Feb 2020 We have 3 papers accepted to CVPR 2020. Congratulations to all authors!
Jan 2020 We have 1 paper accepted to TPAMI.
Dec 2019 We release the TensforFlow code and pre-trained models for ICCV19MST at MST. The PyTorch code for MST is on the way.
Apr 2019 We release all the train/test codes and pre-trained models for ICLR19RNAN at RNAN.
Dec 2018 We have 1 paper accepted to ICLR 2019.
Jul 2018 We have 1 paper accepted to ACM MM 2018 and 1 paper accepted to ECCV 2018. PyTorch version for our CVPR18RDN has been implemented by Nguyễn Trần Toàn (trantoan060689@gmail.com) and merged into EDSR-PyTorch.
Jun 2018 I accept the invitation to serve as Program Committee member of AAAI 2019.
Feb 2018 I will intern to Adobe Research (San Jose, CA) this summer. We have 1 paper accepted to CVPR 2018 as spotlight. All the codes are available at Github.
Jul 2017 I recieve ‘Excellent Graduate of Beijing’ award, ‘Excellent Graduate in Department of Automation, Tsinghua University’ award, Excellent Master Thesis Award, Tsinghua University’ award, and Shenzhen Universiade International Scholarship.
May 2017 We have 1 IEEE TSMC paper accepted. Our team (HelloSR: Xintao Wang, Yapeng Tian, Ke Yu, Yulun Zhang, Shixiang Wu, Chao Dong, Liang Lin, Yu Qiao) ranks 2nd place in NTIRE Image Super-Resolution Challenge.

Recent Publications

  1. arXiv
    QuantCache：Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation
    Junyi Wu†, Zhiteng Li†, Zheng Hui, Yulun Zhang*, Linghe Kong, and Xiaokang Yang
    arXiv preprint arXiv:2503.06545 (arXiv), 2025
    PDF Code
  2. arXiv
    AdaSVD: Adaptive Singular Value Decomposition for Large Language Models
    Zhiteng Li†, Mingyuan Xia†, Jingyuan Zhang, Zheng Hui, Linghe Kong*, Yulun Zhang*, and Xiaokang Yang
    arXiv preprint arXiv:2502.01403 (arXiv), 2025
    PDF Code
  3. arXiv
    One-Step Diffusion Model for Image Motion-Deblurring
    Xiaoyang Liu, Yuquan Wang, Zhen Chen, Jiezhang Cao, He Zhang, Yulun Zhang*, and Xiaokang Yang
    arXiv preprint arXiv:2503.06537 (arXiv), 2025
    PDF Code
  4. arXiv
    QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
    Libo Zhu†, Haotong Qin†, Kaicheng Yang, Wenbo Li, Yong Guo, Yulun Zhang*, Susanto Rahardj, and Xiaokang Yang
    arXiv preprint arXiv:2503.05584 (arXiv), 2025
    PDF Code
  5. arXiv
    CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution
    Kai Liu†, Dehui Wang†, Zhiteng Li, Zheng Chen, Yong Guo, Wenbo Li, Linghe Kong*, and Yulun Zhang*
    arXiv preprint arXiv:2502.15478 (arXiv), 2025
    PDF Code
  6. arXiv
    Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
    Jinpei Guo, Zheng Chen, Wenbo Li, Yong Guo, and Yulun Zhang*
    arXiv preprint arXiv:2502.09873 (arXiv), 2025
    PDF Code
  7. arXiv
    BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
    Kai Liu†, Kaicheng Yang†, Zheng Chen, Zhiteng Li, Yong Guo, Wenbo Li, Linghe Kong*, and Yulun Zhang*
    arXiv preprint arXiv:2312.05541 (arXiv), 2025
    PDF Code
  8. arXiv
    Human Body Restoration with One-Step Diffusion Model and A New Benchmark
    Jue Gong†, Jingkai Wang†, Zheng Chen, Xing Liu, Hong Gu, Yulun Zhang*, and Xiaokang Yang
    arXiv preprint arXiv:2502.01411 (arXiv), 2025
    PDF Code
  9. arXiv
    Progressive Binarization with Semi-Structured Pruning for LLMs
    Xianglong Yan†, Tianao Zhang†, Zhiteng Li, and Yulun Zhang*
    arXiv preprint arXiv:2502.01705 (arXiv), 2025
    PDF Code
  10. arXiv
    One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation
    Jianze Li†, Jiezhang Cao†, Yong Guo, Wenbo Li, and Yulun Zhang*
    arXiv preprint arXiv:2502.01993 (arXiv), 2025
    PDF Code
  11. arXiv
    Grounding-IQA: Multimodal Language Grounding Model for Image Quality Assessment
    Zheng Chen, Xun Zhang, Wenbo Li, Renjing Pei, Fenglong Song, Xiongkuo Min, Xiaohong Liu, Xin Yuan, Yong Guo, and Yulun Zhang*
    arXiv preprint arXiv:2411.17237 (arXiv), 2024
    PDF Code Website
  12. arXiv
    Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment
    Kai Liu†, Ziqing Zhang†, Wenbo Li, Renjing Pei, Fenglong Song, Xiaohong Liu, Linghe Kong*, and Yulun Zhang*
    arXiv preprint arXiv:2410.02505 (arXiv), 2024
    PDF Code
  13. arXiv
    Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution
    Jianze Li, Jiezhang Cao, Zichen Zou, Xiongfei Su, Xin Yuan, Yulun Zhang*, Yong Guo, and Xiaokang Yang
    arXiv preprint arXiv:2410.04224 (arXiv), 2024
    PDF Code
  14. arXiv
    Dual Hyperspectral Mamba for Efficient Spectral Compressive Imaging
    Jiahua Dong, Hui Yin, Hongliu Li, Wenbo Li, Yulun Zhang*, Salman Khan, and Fahad Shahbaz Khan
    arXiv preprint arXiv:2406.00449 (arXiv), 2024
    PDF Code
  15. arXiv
    DPoser: Diffusion Model as Robust 3D Human Pose Prior
    Junzhe Lu, Jing Lin, Hongkun Dou, Yulun Zhang*, Yue Deng, and Haoqian Wang*
    arXiv preprint arXiv:2312.05541 (arXiv), 2023
    PDF Code Website
  16. arXiv
    Image Super-Resolution with Text Prompt Diffusion
    Zheng Chen, Yulun Zhang, Jinjin Gu, Xin Yuan, Linghe Kong, Guihai Chen, and Xiaokang Yang
    arXiv preprint arXiv:2311.14282 (arXiv), 2023
    PDF Code
  17. arXiv
    Binarized 3D Whole-body Human Mesh Recovery
    Zhiteng Li, Yulun Zhang, Jing Lin, Haotong Qin, Jinjin Gu, Xin Yuan, Linghe Kong, and Xiaokang Yang
    arXiv preprint arXiv:2311.14323 (arXiv), 2023
    PDF Code
  18. CVPR
    OSDFace: One-Step Diffusion Model for Face Restoration
    Jingkai Wang†, Jue Gong†, Lin Zhang, Zheng Chen, Xing Liu, Hong Gu, Yutong Liu*, Yulun Zhang*, and Xiaokang Yang
    In Computer Vision and Pattern Recognition (CVPR), 2025
    PDF Code Website
  19. CVPR
    PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
    Libo Zhu, Jianze Li, Haotong Qin*, Wenbo Li, Yulun Zhang*, Yong Guo, and Xiaokang Yang
    In Computer Vision and Pattern Recognition (CVPR), 2025
    PDF Code
  20. ICLR
    ARB-LLM: Alternating Refined Binarizations for Large Language Models
    Zhiteng Li†, Xianglong Yan†, Tianao Zhang, Haotong Qin, Dong Xie, Jiang Tian, Zhongchao Shi, Linghe Kong*, Yulun Zhang*, and Xiaokang Yang
    In International Conference on Learning Representations (ICLR), 2025
    PDF Code
  21. ICLR
    Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
    Chunming He, Chengyu Fang, Yulun Zhang*, Tian Ye, Kai Li, Longxiang Tang, Zhenhua Guo, Xiu Li*, and Sina Farsiu
    In International Conference on Learning Representations (ICLR), 2025
    PDF Code
  22. NeurIPS
    Binarized Diffusion Model for Image Super-Resolution
    Zheng Chen, Haotong Qin*, Yong Guo, Xiongfei Su, Xin Yuan, Linghe Kong, and Yulun Zhang*
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    PDF Code
  23. NeurIPS
    2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
    Kai Liu, Haotong Qin, Yong Guo, Xin Yuan, Linghe Kong*, Guihai Chen, and Yulun Zhang*
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    PDF Code
  24. NeurIPS
    HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
    Yuanhao Cai, Zihao Xiao, Yixuan Liang, Minghan Qin, Yulun Zhang*, Xiaokang Yang, Yaoyao Liu, and Alan Yuille
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    PDF Code
  25. ECCV
    Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis
    Yuanhao Cai, Yixun Liang, Jiahao Wang, Angtian Wang, Yulun Zhang*, Xiaokang Yang, Zongwei Zhou*, and Alan Yuille
    In European Conference on Computer Vision (ECCV), 2024
    PDF Code
  26. ICML
    See More Details: Efficient Image Super-Resolution by Experts Mining
    Eduard Zamfir, Zongwei Wu*, Nancy Mehta, Yulun Zhang*, and Radu Timofte
    In International Conference on Machine Learning (ICML), 2024
    PDF Code
  27. CVPR
    Equivariant Multi-Modality Image Fusion
    Zixiang Zhao, Haowen Bai, Jiangshe Zhang, Yulun Zhang*, Kai Zhang, Shuang Xu, Dongdong Chen*, Radu Timofte, and Luc Van Gool
    In Computer Vision and Pattern Recognition (CVPR), 2024
    PDF Code
  28. CVPR
    Deep Equilibrium Diffusion Restoration with Parallel Sampling
    Jiezhang Cao, Yue Shi, Kai Zhang, Yulun Zhang, Radu Timofte, and Luc Van Gool
    In Computer Vision and Pattern Recognition (CVPR), 2024
    PDF Code
  29. ICLR
    Recursive Generalization Transformer for Image Super-Resolution
    Zheng Chen, Yulun Zhang*, Jinjin Gu, Linghe Kong*, and Xiaokang Yang
    In International Conference on Learning Representations (ICLR), 2024
    PDF Code
  30. ICLR
    Xformer: Hybrid X-Shaped Transformer for Image Denoising
    Jiale Zhang, Yulun Zhang*, Jinjin Gu, Jiahua Dong, Linghe Kong*, and Xiaokang Yang
    In International Conference on Learning Representations (ICLR), 2024
    PDF Code