Zedong Wang (Jacky) is currently a first-year CSE PhD student at The Hong Kong University of Science and Technology (HKUST), advised by Prof. Dan Xu. Previously, he was a visiting student at Westlake University. He received his bachelor's degree in Electronics & Information Engineering from Huazhong University of Science and Technology (HUST), where he was fortunate to be advised by Prof. Xinggang Wang.

His research centers on deep learning, computer vision, and multi-task learning, with a specific focus on (i) efficient model architectures, (ii) unified perception/understanding/generation frameworks, and (iii) optimizers. He has been recognized as Outstanding/Notable Reviewer at several prestigious conferences, including ICLR 2025, ECCV 2024, ACM MM 2024, and BMVC 2024.

News

Research Interests

Currently, I focus mostly on Computer Vision, Multi-task and Multi-modal Learning, including (but not limited to):

• Data-efficient Learning: Mixup Augmentation [OpenMixup, SAMix], Semi-supervised Learning [SemiReward].
• Efficient Network Architectures: Vision Backbones [MogaNet], Multi-task Architectures [MergeVQ].
• Deep Learning Optimizers: (M)LLM Optimizers [BOCB, SGG], Multi-task Optimizers.

Education

 

         The Hong Kong University of Science and Technology (2025-now)
         • Ph.D. in Computer Science and Engineering.
         • Topics: Multi-task and Multi-modal Learning.
         • Advisor: Prof. Dan Xu.

     Huazhong University of Science and Technology (2019-2023)
     • B.Eng. in Electronic and Information Engineering.
     • Thesis: Efficient ConvNet-based Vision Backbone for Multiple Tasks (Grade: 92/100).
     • Advisor: Prof. Xinggang Wang.

 

Research Experience

 

       ZEEKR Intelligent Technology (2024.04-2025.04)
       • Topics: Efficient Multi-task Optimization.
       • Advisor: Prof. Dan Xu (University-Enterprise Cooperation).

       AI Lab, Westlake University (2022.07-2024.02)
       • Topics: Visual Representation Learning and AI for Science.
       • Advisor: Chair Prof. Stan Z. Li (IEEE Fellow, IAPR Fellow).

     Xinggang Wang's Vision Group, HUST (2021.09-2023.03)
     • Topics: Few-shot Semantic Segmentation.
     • Advisor: Prof. Xinggang Wang.

       SIAT-MMLab, Chinese Academy of Sciences (2021.06-2021.09)
       • Topics: Semantic Segmentation and Text Spotting.
       • Advisor: Dr. Bin Fu.

 

Selected Awards and Honors

 

Outstanding/Notable Reviewer Award:

• The 13th International Conference on Learning Representations (ICLR 2025), (rate: 2.6%, 473/18323).
• The 18th European Conference on Computer Vision (ECCV 2024), (rate: 2.7%, 198/7293).
• The 32nd ACM International Conference on Multimedia (ACM MM 2024), (rate: 139/x).
• The 35th British Machine Vision Conference (BMVC 2024), (rate: 19.3%, 166/860)

Publications

Selected Preprints (*: Equal Contribution. †: Corresponding Author.):

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning Siyuan Li*, Juanxi Tian*, Zedong Wang*, Luyuan Zhang, Zicheng Liu, Weiyang Jin, Yang Liu, Baigui Sun, Stan Z. Li† arXiv, 2024 [arXiv] [🤗HF] [Project] [Code] [BibTeX]

Switch EMA: A Free Lunch for Better Flatness and Sharpness Siyuan Li*, Zicheng Liu*, Juanxi Tian*, Ge Wang*, Zedong Wang, Weiyang Jin, Di Wu, Cheng Tan, Tao Lin, Yang Liu, Baigui Sun, Stan Z. Li† arXiv, 2024 [arXiv] [🤗HF] [Code] [BibTeX]

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond Siyuan Li*, Luyuan Zhang*, Zedong Wang, Di Wu, Lirong Wu, Zicheng Liu, Jun Xia, Cheng Tan, Yang Liu, Baigui Sun, Stan Z. Li† arXiv, 2023 [arXiv] [Code] [BibTeX]

Conferences (As First Author):

Taming LLMs by Scaling Learning Rates with Gradient Grouping Siyuan Li*, Juanxi Tian* Zedong Wang*, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu The 63rd Annual Meeting of the Association for Computational Linguistics (ACL Main), 2025 [arXiv] [🤗HF] [BibTeX]

MogaNet: Multi-order Gated Aggregation Network Siyuan Li*, Zedong Wang*, Zicheng Liu, Cheng Tan, Haitao Lin, Di Wu, Zhiyuan Chen, Jiangbin Zheng, Stan Z. Li† International Conference on Learning Representations (ICLR), 2024 [arXiv] [Code] [Zhihu] [BibTeX]

VQDNA: Unleashing the Power of Vector Quantization for Genomic Sequence Modeling Siyuan Li*, Zedong Wang*, Zicheng Liu, Di Wu, Cheng Tan, Jiangbin Zheng, Yufei Huang, Stan Z. Li† International Conference on Machine Learning (ICML), 2024 [arXiv] [Code] [BibTeX]

Conferences (As Co-author):

[NEW!] MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization Siyuan Li*, Luyuan Zhang*, Zedong Wang, Juanxi Tian, Cheng Tan, Zicheng Liu, Chang Yu, Qingsong Xie, Haonan Lu, Haoqian Wang, Zhen Lei† IEEE/CVF Conference on Computer Vision (CVPR), 2025 [arXiv] [🤗HF DailyPapers Top-1] [Project] [BibTeX]

Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences Zicheng Liu, Siyuan Li, Li Wang, Zedong Wang, Yunfan Liu, Stan Z. Li† International Conference on Machine Learning (ICML), 2024 [arXiv] [Code] [BibTeX]

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory Zicheng Liu, Li Wang, Siyuan Li, Zedong Wang, Haitao Lin, Stan Z. Li† International Joint Conference on Artificial Intelligence (IJCAI), 2024 [arXiv] [Code] [BibTeX]

SemiReward: A General Reward Model for Semi-supervised Learning Siyuan Li*, Weiyang Jin*, Zedong Wang, Fang Wu, Zicheng Liu, Cheng Tan, Stan Z. Li† International Conference on Learning Representations (ICLR), 2024 [arXiv] [Code] [BibTeX]

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning Cheng Tan*, Siyuan Li*, Zhangyang Gao, Wenfei Guan, Zedong Wang, Zicheng Liu, Lirong Wu, Stan Z. Li† Advances in Neural Information Processing Systems (NeurIPS), 2023 [arXiv] [Code] [Zhihu] [BibTeX]

Professional Services

Conference Reviewer/PC Member:

• International Conference on Learning Representations (ICLR), 2024 (TinyPapers), 2025
  
• Annual Conference on Neural Information Processing Systems (NeurIPS), 2024, 2025
  
• International Conference on Machine Learning (ICML), 2024, 2025
  
• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  
• European Conference on Computer Vision (ECCV), 2024
  
• AAAI Conference on Artificial Intelligence (AAAI), 2025
  
• ACM International Conference on Multimedia (ACM MM), 2024
  
• BMVA The British Machine Vision Conference (BMVC), 2024, 2025
  
• IAPR International Conference on Pattern Recognition (ICPR), 2024
  

Journal Reviewer:

• IEEE Transactions on Knowledge and Data Engineering (TKDE)
• IEEE Transactions on Big Data (TBD)

Membership:

• China Computer Federation (CCF), Student Member, 2024-2026
• China Society of Image and Graphics (CSIG), Student Member, 2023

Acknowledgement

My research career cannot be possible without the support from all my awesome mentors, collaborators, and friends:

• Prof. Xinggang Wang, Prof. Yu Zhou at HUST.
• Prof. Stan Z. Li, Dr. Siyuan Li, Dr. Zicheng Liu, Dr. Haitao Lin, Dr. Jiangbin Zheng, Mr. Siqi Ma at Westlake University.
• Prof. Dan Xu, Dr. Zhenxing Mi, Dr. Yuxin Wang, Mr. Yucheng Wang, Mr. Yiwei Chen at HKUST.
• Mr. Aozhong Zhang at SUNY Albany.

 

Beyond academia, I feel incredibly fortunate to met wonderful friends along the way (particularly during my middle and high school years in Shenzhen and two years in Hangzhou). Special thanks to Chloe, we met by chance and both joined Westlake University for summer research in 2022. Thank you for your presence and support these years, and I am deeply grateful for our shared moments. Whether we are still in touch or not, I wish you all the best and a bright future!

 

Even if most of you above may never visit this page, my door is always open for a chat - coffee's on me!

Fragments of Memories

Great memories with my advisors: Prof. Xinggang Wang (HUST).

 

Last Updated:

                                      All Rights Reserved by Zedong Wang. Part of page is generated by jemdoc.