Scholar
Wuyang Li
Google Scholar ID: 3Ml_EbAAAAAJ
EPFL
video generative models
2D/3D visual perception
meta-optics
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,472
H-index
21
i10-index
24
Publications
20
Co-authors
7
list available
Contact
Email
wuyang.li@epfl.ch
GitHub
Open ↗
LinkedIn
Open ↗
Publications
15 items
Harnessing Lightweight Transformer with Contextual Synergic Enhancement for Efficient 3D Medical Image Segmentation
2026
Cited
0
PreferRec: Learning and Transferring Pareto Preferences for Multi-objective Re-ranking
2026
Cited
0
Factorized Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models
2025
Cited
0
Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
2025
Cited
0
RAP: 3D Rasterization Augmented End-to-End Planning
2025
Cited
0
See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
2025
Cited
0
MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy
2025
Cited
0
IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
Three papers (VoxDet, See&Trek, IR3D-Bench) accepted to NeurIPS 2025; VoxDet selected as Spotlight
Two papers accepted to ICCV 2025; MetaScope received perfect scores (6,6,6) and was selected as Highlight
Two co-authored papers (FlexGS, TAO) accepted to CVPR 2025
Two co-authored papers (InstantSplamp, PDH-Diffusion) accepted to ICLR 2025
One co-authored paper (Hide-In-Motion) accepted to ICRA 2025
Two co-authored papers (U-KAN, DPA) accepted to AAAI 2025
Two co-authored papers (ToothMaker, LLM-related) accepted to TMI 2025
One co-authored paper on MRI phenotype prediction foundation model accepted to TMI 2024
One paper on SAM for uncertainty modeling accepted to NeurIPS 2024; named Top Reviewer at NeurIPS 2024
First-author works received Oral presentations at CVPR, ICCV, ECCV, and AAAI between Aug 2021 and Aug 2024
Paper CLIFF selected as Oral Presentation at ECCV 2024
Open-sourced Stable Video Infinity in Oct 2025
Organizing the first workshop on multi-modal medical foundation models at NeurIPS 2024
Co-authors
7 total
Yixuan Yuan
Associate Professor in Chinese University of Hong Kong
Xinyu Liu
Imperial College London
Chenxin Li
The Chinese University of Hong Kong
Hengyu Liu
The Chinese University of Hong Kong
Xiaoqing Guo
Assistant Professor in Hong Kong Baptist University, Visiting Fellow in University of Oxford
Bo Han
HKBU / RIKEN
Alexandre Alahi
Professor, EPFL
×
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