Zedong Wang

Zedong Wang 王泽栋

I am a CSE PhD student at HKUST, advised by Prof. Dan Xu. I am having a fantastic time at Apple AIML, working with Zizhen Wang and Peng Zhang. I received my B.Eng. from HUST, where I was fortunate to be advised by Prof. Xinggang Wang.

I am grateful to receive outstanding reviewer awards at multiple leading venues, including ICML'26, BMVC'25, ICLR'25 (rate: 2.6%), ECCV'24 (rate: 2.7%), MM'24, and BMVC'24.

Email / Scholar / Twitter / LinkedIn

News

[May 2026] I was recognized as Silver Reviewer at ICML 2026.
[Feb 2026] One paper on image editing, CARE-Edit, got accepted at CVPR 2026. Congrats to Yucheng Wang.
[Nov 2025] I was recognized as Outstanding Reviewer at BMVC 2025 (rate: 21.3%, 247/1,161).
[Oct 2025] I received the Best Reviewer Award at UniReps 2025 (1 of the 2 awardees).
[Jul 2025] One paper on multi-task learning, Rep-MTL, got accepted at ICCV 2025 (Highlight, top 2.3%).
[May 2025] I was recognized as Notable Reviewer at ICLR 2025 (rate: 2.6%, 473/18,323).
[Apr 2025] One paper on image generation, MergeVQ, got accepted at CVPR 2025. Congrats to Siyuan Li.
[Mar 2025] My proposal to introduce separate Borderline Accept/Reject (BA/BR) ratings for initial reviews was acknowledged by the ICCV'25 program chairs and officially adopted at ICCV 2025.
[Nov 2024] I was recognized as Outstanding Reviewer at BMVC 2024 (rate: 19.3%, 166/860).
[Nov 2024] I was recognized as Outstanding Reviewer at ACM MM 2024.
[Sep 2024] I was recognized as Outstanding Reviewer at ECCV 2024 (rate: 2.7%, 198/7,293).

Experience

Apple | AIML

Research Intern

Hosts: Zizhen Wang

Mar 2026 – Present

Research

My overarching goal is to build scalable multimodal foundation models that understand, reason, and interact with the world as holistically as humans do. Specifically, I worked on (i) multi-task learning: Rep-MTL (ICCV'25 Highlight, top 2.3%), (ii) multi-modal understanding and generation: CARE-Edit (CVPR'26), (iii) efficient model architectures: MogaNet (ICLR'24).

	CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing Yucheng Wang, Zedong Wang, Yuetong Wu, Yue Ma, Dan Xu IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026 arXiv / project / Hugging Face / video A condition-aware mixture-of-experts framework for contextual image editing.
	Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning Zedong Wang, Siyuan Li, Dan Xu IEEE/CVF International Conference on Computer Vision (ICCV), 2025 (Highlight, Top 2.3%) arXiv / project / Hugging Face / video Exploiting representation-level task saliency for effective multi-task learning.
	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 and Pattern Recognition (CVPR), 2025 arXiv / project / Hugging Face (Top-1 paper of the day) A unified framework for visual generation and representation with disentangled token merging and quantization. Ranked top 1 at Hugging Face Daily Papers on Apr 3rd, 2025.
	Taming LLMs by Scaling Learning Rates with Gradient Grouping Siyuan Li, Juanxi Tian, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu Annual Meeting of the Association for Computational Linguistics (ACL)*, 2025 arXiv / project / Hugging Face Taming LLMs by scaling learning rates with gradient grouping.
	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 / project Multi-order gated aggregation network for efficient vision backbone.
	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 / project Short-long convolutions with linear attention for long sequence modeling.
	OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning Siyuan Li, Zedong Wang, Zicheng Liu, Di Wu, Stan Z. Li arXiv preprint, 2022 arXiv / project Open source mixup augmentation benchmark for visual representation learning.

Awards and Recognitions

Awards:

2026 Silver Reviewer, at ICML 2026
2025 Outstanding Reviewer (21.3%, 247/1,161), at BMVC 2025
2025 Outstanding Reviewer (1 of 22 awardees), at NLDL 2026
2025 Best Reviewer Award (one of the two awardees), at UniReps workshop at NeurIPS 2025
2025 Notable Reviewer (2.6%, 473/18,323), at ICLR 2025
2024 Outstanding Reviewer (2.7%, 198/7,293), at ECCV 2024
2024 Outstanding Reviewer (19.3%, 166/860), at BMVC 2024
2024 Outstanding Reviewer (1 of 139 awardees), at ACM MM 2024

Recognitions:

2025 Broadening Participation Award, at ICCV 2025
2025 Highlight Presentation (rate: 2.3%), at ICCV 2025

Services

Conference Reviewer / PC Member:

International Conference on Learning Representations (ICLR), 2024 (TinyPapers), 2025, 2026
Annual Conference on Neural Information Processing Systems (NeurIPS), 2024, 2025
International Conference on Machine Learning (ICML), 2024, 2025, 2026
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, 2026
European Conference on Computer Vision (ECCV), 2024, 2026
AAAI Conference on Artificial Intelligence (AAAI), 2025
ACM International Conference on Multimedia (ACM MM), 2024
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2026
The British Machine Vision Conference (BMVC), 2024, 2025, 2026
International Conference on Pattern Recognition (ICPR), 2024
Northern Lights Deep Learning Conference (NLDL), 2026

Journal Reviewer:

IEEE Transactions on Image Processing (TIP)
Transactions on Machine Learning Research (TMLR)
IEEE Transactions on Knowledge and Data Engineering (TKDE)

Membership:

Student Member at BMVA, 2025-present
Member at CVF, 2025-present
Student Member at CCF, 2024-2026
Student Member at CSIG, 2023-2024

Teaching Assistant:

COMP 5212 Machine Learning, Fall 2025

Acknowledgement

My research would not be possible without the support of my awesome mentors, collaborators, and friends:

Prof. Xinggang Wang at Huazhong University of Science and Technology.
Mr. Siyuan Li, Mr. Zicheng Liu, Mr. Haitao Lin, Mr. Jiangbin Zheng at Westlake University.
Prof. Dan Xu, Mr. Zhenxing Mi, Mr. Yuxin Wang, Mr. Shaocong Dong, Mr. Chi Yan, Mr. Yucheng Wang, Mr. Yiwei Chen, Mr. Jiehui Huang at HKUST.
Mr. Zizhen Wang, Mr. Peng Zhang at Apple.

Beyond academia, I've been fortunate to meet some truly wonderful friends along the way, especially during my six years of middle and high school in Shenzhen. You've seen me at my most naive and know all the stupid things I've done. I cherish the time we shared, it shaped my unguarded youth and, in more ways than I realize, still carries me today. As you once put it: "We grew up together." Wherever life has taken us, I wish you nothing but the best. My door is always open — coffee's on me!

Last updated Apr. 2026. Template from Jon Barron.