Yijun Li

Adobe Systems (United States) — United States

Computer Science · Physical Sciences

24h-index3.8kcitations98works1.32yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Generative Adversarial Networks and Image Synthesis(43), Advanced Image Processing Techniques(20), Computer Graphics and Visualization Techniques(17), Advanced Vision and Imaging(17), Advanced Image and Video Retrieval Techniques(13)

Publications98 total

Motion Inversion for Video Customization
2025· 1 cited
Generative Image Layer Decomposition with Visual Effects
2025
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
2025· 4 cited
X-Fusion: Introducing New Modality to Frozen Large Language Models
arXiv (Cornell University)·2025Open Access
ArmorCLIP: a hybrid defense strategy for boosting adversarial robustness in vision-language models
2025Open Access
Influence of blockage ratio and length-to-diameter ratio on explosion dynamics of DME/H2 blended gas in semi-open space
Energy·2025· 4 cited
UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
arXiv (Cornell University)·2024Open Access
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors
arXiv (Cornell University)·2024Open Access
Generative Image Layer Decomposition with Visual Effects
arXiv (Cornell University)·2024Open Access
Text-Anchored Score Composition: Tackling Condition Misalignment in Text-to-Image Diffusion Models
Lecture notes in computer science·2024· 3 cited
Removing Distributional Discrepancies in Captions Improves Image-Text Alignment
Lecture notes in computer science·2024
A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models
arXiv (Cornell University)·2024Open Access
Removing Distributional Discrepancies in Captions Improves Image-Text Alignment
arXiv (Cornell University)·2024Open Access
Separate-and-Enhance: Compositional Finetuning for Text-to-Image Diffusion Models
2024· 3 citedOpen Access
MAGICK: A Large-Scale Captioned Dataset from Matting Generated Images Using Chroma Keying
2024· 3 cited
Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
2024· 3 cited
Motion Inversion for Video Customization
arXiv (Cornell University)·2024Open Access
P2D: Plug and Play Discriminator for accelerating GAN frameworks
2024· 1 cited
Consistent Multimodal Generation via A Unified GAN Framework
2024· 2 cited
Separate-and-Enhance: Compositional Finetuning for Text2Image Diffusion Models
arXiv (Cornell University)·2023Open Access
page 1 of 5Next →

Frequent Co-authors

Ming–Hsuan Yang(20), Jingwan Lu(10), Shuicheng Yan(8), Fang Chen(7), Zhaowen Wang(6), Eli Shechtman(6), Richard Zhang(5), Krishna Kumar Singh(5), Yong Jae Lee(4), Nuno Vasconcelos(4), Zhe Lin(3), Magdy Bayoumi(3), Sifei Liu(2), Xueting Li(2), Jan Kautz(2), Xin Lü(2), Gaurav Parmar(2), Krishna Kumar Singh(2), Jun-Yan Zhu(2), Xin Lü(2)