Portrait of Yongsheng Yu

Yongsheng Yu

Visual generation: pixel-space diffusion, editing & restoration.

Ph.D. candidate in the VIStA Lab at the University of Rochester, advised by Albert Arendt Hopeman Professor Jiebo Luo. I've interned at NVIDIA, Adobe Research, and Microsoft Research Asia.

On the job market, planning to graduate in 2027.

News

10/2026
ZipIR-powered Firefly Upscaler 2 is now in Adobe Photoshop Beta, with 6×/8× upscaling up to 67 MP (8192×8192)!
09/2026
PixelDiT2 and Aurora are accepted to NeurIPS 2026!
09/2026
I will serve as an Area Chair for CVPR 2027.
06/2026
PixelDiT is selected as a CVPR 2026 Best Paper Finalist!
02/2026
PixelDiT is accepted to CVPR 2026 Oral
12/2025
I will serve as an Area Chair for ECCV 2026.
11/2025
RealUHR is accepted to AAAI 2026.
09/2025
PixPerfect 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
MaGIC is accepted to ICLR 2024.

Show more

Experience

NVIDIA
Research Intern · Santa Clara, US
June 2026 - Present
Developing next-generation DLSS (beyond DLSS 5)
Research Intern · Santa Clara, US
May 2025 - May 2026
Research on the PixelDiT series (PixelDiT, PixelDiT2)
Adobe Research
May 2024 - Apr 2025
Research Intern · San Jose, US
Research on high-resolution image restoration (ZipIR), now shipped in Adobe Photoshop
Microsoft Research Asia
May 2023 - Aug 2023
Research Intern · Beijing, China

Selected Publications

NeurIPS 2026
PixelDiT2: Representation-Grounded Pixel Diffusion Transformers
Yongsheng Yu, Wei Xiong, Yichen Sheng, Shiqiu Liu, Jiebo Luo
Project PDF Code ImageNet Model
PixelDiT
CVPR 2026 Oral Best Paper Finalist
PixelDiT: Pixel Diffusion Transformers for Image Generation
Yongsheng Yu, Wei Xiong, Weili Nie, Yichen Sheng, Shiqiu Liu, Jiebo Luo
Project PDF Code ImageNet Model T2I Model
NeurIPS 2026
Aurora: Unified Video Editing with a Tool-Using Agent
Yongsheng Yu, Ziyun Zeng, Zhiyuan Xiao, Zhenghong Zhou, Hang Hua, Wei Xiong, Jiebo Luo
Project PDF Code Model Dataset
OmniPaint
ICCV 2025
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
Yongsheng Yu*, Ziyun Zeng*, Haitian Zheng, Jiebo Luo
Project PDF Code Model Benchmark
arXiv 2504.08591 Shipped in Photoshop
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
Powers Adobe Firefly Upscaler 2 (Generative Upscale) in Photoshop Beta
PDF
PromptFix
NeurIPS 2024
PromptFix: You Prompt and We Fix the Photo
Yongsheng Yu*, Ziyun Zeng*, Hang Hua, Jianlong Fu, Jiebo Luo
Project PDF Code Dataset
ECCV 2022
Unbiased Multi-Modality Guidance for Image Inpainting
Yongsheng Yu, Dawei Du, Libo Zhang, Tiejian Luo
PDF Code
ECCV 2022
High-Fidelity Image Inpainting with GAN Inversion
Yongsheng Yu, Libo Zhang, Heng Fan, Tiejian Luo
PDF

Services

Area ChairECCV 2026, CVPR 2027
Conference Reviewer 2026: CVPR Outstanding Reviewer, AAAI, NeurIPS
2025: CVPR, ICCV, ICLR, NeurIPS, AAAI, MM
2024: CVPR, ECCV, ICML, ICLR, NeurIPS, ICME, MM, WACV
2023: CVPR, ICCV, NeurIPS, WACV
Journal ReviewerIEEE TIP, IJCV, IEEE TMM