Scholar
Yuanzhi Zhu
Google Scholar ID: 4vm_v9EAAAAJ
PhD student, Ecole Polytechnique
Efficient Generative Models
Visual Enhancement
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
810
H-index
7
i10-index
5
Publications
13
Co-authors
0
Contact
Email
yuanzhi.zhu@polytechnique.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
Publications
1 items
MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution
2026
Cited
0
Resume (English only)
Academic Achievements
Published 'Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings', arXiv:2509.22925.
Paper 'Di[M]O: Distilling Masked Diffusion Models into One-Step Generator' accepted at ICCV (2025), arXiv:2503.15457.
Published 'OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs', arXiv:2412.09465.
Paper 'SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow' accepted at ECCV (2024), arXiv:2407.12718.
Paper 'Denoising Diffusion Models for Plug-and-Play Image Restoration' accepted at CVPRW (2023), arXiv:2305.08995.
Awarded CVPR 2025 Outstanding Reviewer.
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up