Scholar
Yilin Wang
Google Scholar ID: fYqdLx4AAAAJ
Senior Research Scientist, Adobe
Citations & Impact
Citations
1,850
H-index
20
i10-index
33
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 3 papers accepted to CVPR 2025
- 1 paper accepted to AAAI 2025
- OmniStyle: The first end-to-end style transfer framework based on the Diffusion Transformer (DiT) architecture
- FINECAPTION: Compositional Image Captioning
- UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
- SigStyle: Signature Style Transfer via Personalized Text-to-Image Models
- SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing
- UniHuman: A Unified Model for Editing Human Images in the Wild
- Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion
- PHOTOSWAP: Personalized Subject Swapping in Images
- LightPainter: Interactive Portrait Relighting with Freehand Scribble
Research Experience
- Research Scientist at Adobe, primary contributor to features like Instruction-based Image Editing, Select Subject, Object Finder, and Select People Details. Contributed to 8 tech transfers to products including Photoshop, Lightroom, and Stardust.
Education
- Ph.D., Arizona State University, Advisor: Baoxin Li
Background
- Research Interests: Computer Vision, Image Understanding and Editing. Professional Field: Computer Vision for Imaging products at Adobe.
Miscellany
- Now recruiting summer research interns in image/video editing with MLLM (Multimodal Language-Image Model).
Co-authors