Zixin Zhu
I am a Ph.D. student in Computer Science and Engineering at the
University at Buffalo, advised by
Prof. Junsong Yuan.
My research focuses on generative AI for visual content —
diffusion models, text-to-image/video generation and editing,
vision–language grounding, and reinforcement learning for generation (RLHF / GRPO).
I am currently a research intern at ByteDance (Intelligent Creation, Seattle WA).
Previously I interned at Adobe (2024 & 2025), Pixocial (remote), and
Microsoft Research Asia (2021–2023).
Before UB, I received my M.S. from Xi'an Jiaotong University, where I worked on
temporal action localization with
Prof. Le Wang.
News
- 2026.05Joined ByteDance Intelligent Creation team as a research intern in Seattle, WA.
- 2026.02One paper accepted to CVPR 2026: Learning 3D Shape Fidelity Metric from Real-world Distortions.
- 2025.09GeoRemover is accepted to NeurIPS 2025 as a Spotlight!
- 2025.06CompSlider is accepted to ICCV 2025.
- 2025.05Started a research internship at Adobe, San Jose (user intent modeling in image editing).
Publications
Selected works; full list on Google Scholar. * denotes equal contribution.
NeurIPS'25
Zixin Zhu, Haoxiang Li, Xuelu Feng, He Wu, Chunming Qiao, Junsong Yuan
NeurIPS 2025 (Spotlight)
CVPR'26
Learning 3D Shape Fidelity Metric from Real-world Distortions
Xuelu Feng, Tianyu Luan, Zixin Zhu, Akshobhya Sharma, Phani Nuney, Junsong Yuan, Chunming Qiao
CVPR 2026
ICCV'25
Zixin Zhu, Kevin Duarte, Mamshad Nayeem Rizve, Chengyuan Xu, Ratheesh Kalarot, Junsong Yuan
ICCV 2025
ECCV'24
Zixin Zhu, Xuelu Feng, Dongdong Chen, Junsong Yuan, Chunming Qiao, Gang Hua
ECCV 2024
arXiv
Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua
arXiv preprint
arXiv
Zixin Zhu, Yixuan Wei, Jianfeng Wang, Zhe Gan, Zheng Zhang, Le Wang, Gang Hua, Lijuan Wang, Zicheng Liu, Han Hu
arXiv preprint
T-PAMI
ContextLoc++: A Unified Context Model for Temporal Action Localization
Zixin Zhu, Le Wang, Wei Tang, Nanning Zheng, Gang Hua
IEEE T-PAMI, vol. 45, no. 8, 2023
AAAI'22
Zixin Zhu, Le Wang, Wei Tang, Ziyi Liu, Nanning Zheng, Gang Hua
AAAI 2022
ICCV'21
Zixin Zhu, Wei Tang, Le Wang, Nanning Zheng, Gang Hua
ICCV 2021
Experience
2026.05 – now
ByteDance, Seattle WA — Research Intern, Intelligent Creation
2025.05 – 2025.08
Adobe, San Jose CA — Research Intern (user intent modeling in image editing)
2024.12 – 2025.02
Pixocial Technology, Singapore — Research Intern, remote from China (object removal, NeurIPS'25 Spotlight)
2024.05 – 2024.08
Adobe, San Jose CA — Research Intern (attribute sliders for diffusion, ICCV'25)
2023.01 – 2023.06
Microsoft Research Asia, Beijing — Part-time Research Intern (asymmetric VQGAN)
2021.12 – 2022.06
Microsoft Research Asia, Beijing — Research Intern (diffusion models for text generation)
Academic Service
Reviewer for T-PAMI, IJCV, TMM, CVIU, Pattern Recognition, Machine Vision and Applications, and other journals; reviewer for CVPR, ECCV, NeurIPS, and ACM Multimedia. Program Committee Member, AAAI 2026.
