(Photo Credit: Songwei Ge)
Sheng-Yu Wang

PhD Student
Carnegie Mellon University

shengyu2 at andrew.cmu.edu
[GitHub] [Google Scholar]


I am a PhD student at CMU, advised by Jun-Yan Zhu. These days, I am also working closely with Richard Zhang, Alexei (Alyosha) Efros, Aaron Hertzmann, and David Bau. I am generally interested in analyzing neural networks and modeling the physical world. During undergrad, I worked at BAIR with Oliver Wang, Richard Zhang, Andrew Owens and Alexei (Alyosha) Efros. In the past, I have worked on image synthesis, image forensics, and condensed matter physics.


Publications

Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
Sheng-Yu Wang, Aaron Hertzmann, Alexei A. Efros, Jun-Yan Zhu, Richard Zhang.
In NeurIPS, 2024.
[Paper] [Webpage] [GitHub] [Bibtex]
Customizing Text-to-Image Models with a Single Image Pair
Maxwell Jones, Sheng-Yu Wang, Nupur Kumari, David Bau, Jun-Yan Zhu.
In SIGGRAPH Asia, 2024.
[Paper] [Webpage] [GitHub] [Bibtex]
Evaluating Data Attribution for Text-to-Image Models
Sheng-Yu Wang, Alexei A. Efros, Jun-Yan Zhu, Richard Zhang.
In ICCV, 2023.
[Paper] [Webpage] [GitHub] [Bibtex]
Ablating Concepts in Text-to-Image Diffusion Models
Nupur Kumari, Bingliang Zhang, Sheng-Yu Wang, Eli Shechtman, Richard Zhang, Jun-Yan Zhu.
In ICCV, 2023.
[Paper] [Webpage] [GitHub] [Bibtex]
Content-Based Search for Deep Generative Models
Daohan Lu*, Sheng-Yu Wang*, Nupur Kumari*, Rohan Agarwal*, Mia Tang, David Bau, Jun-Yan Zhu.
In SIGGRAPH Asia, 2023.
[Modelverse] [Webpage] [Github] [Paper] [Video] [BibTex]
Rewriting Geometric Rules of a GAN
Sheng-Yu Wang, David Bau, Jun-Yan Zhu.
In SIGGRAPH, 2022.
[Paper] [Webpage] [GitHub] [Bibtex]
Sketch Your Own GAN
Sheng-Yu Wang, David Bau, Jun-Yan Zhu.
In ICCV, 2021.
[Paper] [Webpage] [GitHub] [Bibtex]
CNN-generated images are surprisingly easy to spot...for now
Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, Alexei A. Efros.
In CVPR, 2020 (oral presentation).
[Paper] [Webpage] [GitHub] [Bibtex]
Detecting Photoshopped Faces by Scripting Photoshop
Sheng-Yu Wang, Oliver Wang, Andrew Owens, Richard Zhang, Alexei A. Efros.
In ICCV, 2019.
[Paper] [Webpage] [GitHub] [Poster] [Adobe Max] [Bibtex]
Reversible writing of high mobility and high carrier density doping patterns in two-dimensional van der Waals heterostructures
Wu Shi, Salman Khan, Lili Jiang, Sheng-Yu Wang, Hsin-Zon Tsai, Dillon Wong, Takashi Taniguchi, Kenji Watanabe, Fen Wang, Michael Crommie, Alex Zettl.
Nature Electronics.
[Paper]
Many thanks to Richard Zhang for sharing his website template!