Yaxing Wang的主页

Yaxing is an associate professor of college of computer science at Nankai University. His research interests include GANs, image-to-image translation, domain adaptation and lifelong learning.

Research Interests：

My research covers a range of GAN, Transfer Learning, Domain Adaptation and Lifelong learning.

See my recent publications for more details.

News

Group

Ph.D. Students

Senmao Li (Diffusion Model, 2022-)
Kangneng Zhou (3D Vision, 2023-)
Linxuan Li (Diffusion Model, 2024-)
Yang Cheng (Diffusion Model, 2024-)

Master Students

Taihang Hu (Diffusion Model, 2023-)
Tao Liu (Diffusion Model, 2024-)

Preprint

InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration
_{Senmao Li, Kai Wang, Joost van de Weijer, Fahad Shahbaz Khan, Chun-Le Guo, Shiqi Yang, Yaxing Wang, Jian Yang, Ming-Ming Cheng
arxiv, 2025
[Arxiv]}

Selected Journal Publications (Google Scholar)

Minegan++: Mining generative models for efficient knowledge transfer to limited data domains
_{Yaxing Wang, Abel Gonzalez-Garcia, Chenshen Wu, Luis Herranz, Fahad Shahbaz Khan, Shangling Jui, Jian Yang, Joost van de Weijer
IJCV, 2024
[paper]}

Stylediffusion: Prompt-embedding inversion for text-based editing
_{Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, Jian Yang
CVMJ, 2024
[paper] [code]}

Selected Conference Publications (Google Scholar)

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing
_{Taihang Hu, Linxuan Li, Kai Wang, Yaxing Wang, Jian Yang, Ming-Ming Cheng
ICCV, 2025
[paper] [code]}

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
_{Tao Liu, Kai Wang, Senmao Li, Joost van de Weijer, Fahad Shahbaz Khan, Shiqi Yang, Yaxing Wang, Jian Yang, Ming-Ming Cheng
ICLR, 2025
[paper]}

Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
_{Lei Wang, Senmao Li, Fei Yang, Jianye Wang, Ziheng Zhang, Yuhan Liu, Yaxing Wang, Jian Yang
CVPR, 2025
[paper]}

One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models
_{Senmao Li, Lei Wang, Kai Wang, Tao Liu, Jiehang Xie, Joost van de Weijer, Fahad Shahbaz Khan, Shiqi Yang, Yaxing Wang, Jian Yang
CVPR, 2025
[paper] [code]}

Token merging for training-free semantic binding in text-to-image synthesis
_{Taihang Hu, Linxuan Li, Joost van de Weijer, Hongcheng Gao, Fahad Shahbaz Khan, Jian Yang, Ming-Ming Cheng, Kai Wang, Yaxing Wang
Neuips, 2024
[paper] [code]}

Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
_{Senmao Li, Joost van de Weijer, Fahad Khan, Tao Liu, Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng
Neuips, 2024
[paper] [code]}

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
_{Senmao Li, Joost van de Weijer, Taihang Hu, Fahad Shahbaz Khan, Qibin Hou, Yaxing Wang, Jian Yang
ICLR, 2024
[paper] [code]}

Adaptive texture filtering for single-domain generalized segmentation
_{Xinhui Li, Mingjia Li, Yaxing Wang, Chuan-Xian Ren, Xiaojie Guo
AAAI, 2023
[paper]}

3D-aware multi-class image-to-image translation with NeRFs
_{Senmao Li, Joost Van De Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang
CVPR, 2023
[paper] [code]}

Yaxing Wang (王亚星)

Research Interests：

News

Group

Ph.D. Students

Master Students

Preprint

InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration

Selected Journal Publications (Google Scholar)

Minegan++: Mining generative models for efficient knowledge transfer to limited data domains

Stylediffusion: Prompt-embedding inversion for text-based editing

Selected Conference Publications (Google Scholar)

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt

Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability

One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models

Token merging for training-free semantic binding in text-to-image synthesis

Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models

Adaptive texture filtering for single-domain generalized segmentation

3D-aware multi-class image-to-image translation with NeRFs

Academic Services

Honors and Awards