Yuxin Zhang
Researcher of Generative AI
yuxin.zhazel [at] gmail [dot] com
About Me
I recently joined ByteDance as a Researcher of Generative AI. Previously, I received my Ph.D. in Computer Science from the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, advised by Prof. Changsheng Xu and Prof. Weiming Dong. I obtained my B.S. in Automation from Tsinghua University in 2020.
My research sits at the intersection of Computer Vision and Computer Graphics, focusing on building interactive, interpretable, and creative generative models. Currently, I work on Generative AI, Multimedia, and Computational Art.
News
- 2025.05 🎉 MotionCrafter: Plug-and-Play Motion Guidance for Diffusion Models accepted to IEEE TVCG [Code]
- 2025.04 🎉 B4M: Breaking Low-Rank Adapter for Making Content-Style Customization accepted to ACM TOG [Code]
- 2025.01 🎉 IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting accepted to ACM SIGGRAPH 2025 [Code]
Work Experience
ByteDance
Researcher of Generative AI
July 2025 – Present
Researcher of Generative AI
July 2025 – Present
Publications
IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting
Y Zhang, M Luo, W Dong, X Yang, H Huang, C Ma, O Deussen, TY Lee, CS Xu
SIGGRAPH 2025 [Code]
Y Zhang, M Luo, W Dong, X Yang, H Huang, C Ma, O Deussen, TY Lee, CS Xu
SIGGRAPH 2025 [Code]
MotionCrafter: Plug-and-Play Motion Guidance for Diffusion Models
Y Zhang, W Dong, F Tang, N Huang, H Huang, C Ma, C Xu
IEEE TVCG [Code]
Y Zhang, W Dong, F Tang, N Huang, H Huang, C Ma, C Xu
IEEE TVCG [Code]
Inversion-Based Style Transfer With Diffusion Models
Y Zhang, N Huang, F Tang, H Huang, C Ma, W Dong, C Xu
CVPR 2023 [Code]
Y Zhang, N Huang, F Tang, H Huang, C Ma, W Dong, C Xu
CVPR 2023 [Code]
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning
Y Zhang, F Tang, W Dong, H Huang, C Ma, TY Lee, C Xu
SIGGRAPH 2022 [Code]
Y Zhang, F Tang, W Dong, H Huang, C Ma, TY Lee, C Xu
SIGGRAPH 2022 [Code]
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
Y Zhang, W Dong, F Tang, N Huang, H Huang, C Ma, TY Lee, O Deussen, C Xu
SIGGRAPH Asia 2023 / ACM TOG [Code]
Y Zhang, W Dong, F Tang, N Huang, H Huang, C Ma, TY Lee, O Deussen, C Xu
SIGGRAPH Asia 2023 / ACM TOG [Code]
A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning
Y Zhang, F Tang, W Dong, H Huang, C Ma, TY Lee, C Xu
ACM TOG [Code]
Y Zhang, F Tang, W Dong, H Huang, C Ma, TY Lee, C Xu
ACM TOG [Code]
LumiSculpt: A Consistency Lighting Control Network for Video Generation
Y Zhang, D Zheng, B Gong, J Chen, M Yang, W Dong, C Xu
arXiv
Y Zhang, D Zheng, B Gong, J Chen, M Yang, W Dong, C Xu
arXiv
Portrait Map Art Generation by Asymmetric Image-to-Image Translation
Y Zhang, F Tang, W Dong, TNH Le, C Xu, TY Lee
Leonardo
Y Zhang, F Tang, W Dong, TNH Le, C Xu, TY Lee
Leonardo