avatar

Yongsheng Yu

Ph.D. Candidate
University of Rochester
yyu90 at ur.rochester.edu


I am a Ph.D. Candidate at the University of Rochester, working with Professor Jiebo Luo on computer vision and machine learning. My research focuses on visual generation and editing, bridging the gap between human creativity and computational intelligence.

Open to research collaborations! Always happy to explore fun, cutting-edge ideas—feel free to email me to collaborate on something impactful.

News

12/2025
I will serve as an Area Chair for ECCV 2026.
12/2025
See our PixelDiT project page and paper.
11/2025
🎈 Our RealUHR is accepted to AAAI 2025.
09/2025
🎈 One paper is accepted to NeurIPS 2025.
06/2025
🎈 OmniPaint is accepted to ICCV 2025.
04/2025
32×-compressed latent SR model ZipIR report is available! (Completed Nov 2024, delayed release due to patent application)
09/2024
🎈 PromptFix is accepted to NeurIPS 2024.
01/2024
🎈 Our MaGIC is accepted to ICLR 2024.

Experience

NVIDIA
May 2025 - Present
Research Intern
Santa Clara, US
Adobe Research
May 2024 - April 2025
Research Intern
San Jose, US
Microsoft Research Asia
May 2023 - August 2023
Research Intern
Beijing, China

Publications

PixelDiT
PixelDiT: Pixel Diffusion Transformers for Image Generation
Yongsheng Yu, Wei Xiong, Weili Nie, Yichen Sheng, Shiqiu Liu, Jiebo Luo
Preprint, 2025
Project PDF
OmniPaint
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
Yongsheng Yu*, Ziyun Zeng*, Haitian Zheng, Jiebo Luo
ICCV, 2025 GitHub stars
Project PDF Code
ZipIR
ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration
Yongsheng Yu, Haitian Zheng, Zhifei Zhang, Jianming Zhang, Yuqian Zhou, Connelly Barnes, Yuchen Liu, Wei Xiong, Zhe Lin, Jiebo Luo
In submission, 2025
PDF
PromptFix
PromptFix: You Prompt and We Fix the Photo
Yongsheng Yu*, Ziyun Zeng*, Hang Hua, Jianlong Fu, Jiebo Luo
NeurIPS, 2024 GitHub stars
Project PDF Code Dataset
MaGIC
MaGIC: Multi-modality Guided Image Completion
Hao Wang*, Yongsheng Yu*, Tiejian Luo, Heng Fan, Libo Zhang
ICLR, 2024
PDF Website Code
DMT
Deficiency-Aware Masked Transformer for Video Inpainting
Yongsheng Yu, Heng Fan, Libo Zhang, Jiebo Luo
In Submission, 2023
PDF Code
Chain-of-Thought
Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models
Yongsheng Yu, Jiebo Luo
ICME (Oral), 2024
PDF
Unbiased Multi-Modality
Unbiased Multi-Modality Guidance for Image Inpainting
Yongsheng Yu, Dawei Du, Libo Zhang, Tiejian Luo
ECCV, 2022
PDF Code
High-Fidelity Inpainting
High-Fidelity Image Inpainting with GAN Inversion
Yongsheng Yu, Libo Zhang, Heng Fan, Tiejian Luo
ECCV, 2022
PDF

Services

Area Chair
2026
Invited Area Chair for ECCV 2026.
Reviewer
2023–2025
2025: CVPR, ICCV, ICLR, MM, NeurIPS, AAAI, TIP, IJCV
2024: CVPR, ECCV, ICML, ICLR, ICME, MM, NeurIPS, WACV
2023: CVPR, ICCV, NeurIPS, WACV


Powered by Jekyll