Scholar
Fangyun Wei
Google Scholar ID: -ncz2s8AAAAJ
Microsoft Research
Computer Vision
Deep Learning
Generative Models
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
8,095
H-index
38
i10-index
49
Publications
20
Co-authors
20
list available
Contact
No contact links provided.
Publications
13 items
Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
2026
Cited
0
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
2026
Cited
0
InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
2026
Cited
0
MobileManiBench: Simplifying Model Verification for Mobile Manipulation
2026
Cited
0
Animate Any Character in Any World
2025
Cited
0
Spatia: Video Generation with Updatable Spatial Memory
2025
Cited
0
VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
2025
Cited
0
From Virtual Games to Real-World Play
2025
Cited
0
Load more
Resume (English only)
Co-authors
20 total
Han Hu
Distinguished Scientist, Tencent Hunyuan
Stephen Lin
Microsoft Research Asia
Co-author 3
Mengde Xu
Huazhong University of Science and Technology
Hongyang Zhang
Assistant Professor of Computer Science, University of Waterloo
Dong Chen
Principal Research Manager, Microsoft Research Asia
Jianmin Bao
Microsoft Research
Chao Zhang
School of Intelligence Science and Technology
