Yijun Li

papers

1,132

total citations

papers (23)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

CVPR 2025arXiv

citations

Content-Aware GAN Compression

CVPR 2021arXiv

citations

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

CVPR 2022arXiv

citations

Collaging Class-Specific GANs for Semantic Image Synthesis

ICCV 2021arXiv

citations

3D-FM GAN: Towards 3D-Controllable Face Manipulation

ECCV 2022arXiv

citations

IMAGINE: Image Synthesis by Image-Guided Model Inversion

CVPR 2021arXiv

citations

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

CVPR 2024arXiv

citations

Generative Video Propagation

CVPR 2025arXiv

citations

Generative Image Layer Decomposition with Visual Effects

CVPR 2025arXiv

citations

Modeling Artistic Workflows for Image Generation and Editing

ECCV 2020arXiv

citations

TransPixeler: Advancing Text-to-Video Generation with Transparency

CVPR 2025arXiv

citations

X-Fusion: Introducing New Modality to Frozen Large Language Models

ICCV 2025arXiv

citations

Contrastive Learning for Diverse Disentangled Foreground Generation

ECCV 2022arXiv

citations

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

ECCV 2024arXiv

citations

The Causal Impact of Credit Lines on Spending Distributions

AAAI 2024arXiv

citations

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data

AAAI 2025arXiv

citations

Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification

ICCV 2025

citations

Cross-modal Latent Space Alignment for Image to Avatar Translation

ICCV 2023

citations

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying

CVPR 2024

citations

Yijun Li

papers (23)

Few-Shot Image Generation via Cross-Domain Correspondence

Few-shot Image Generation with Elastic Weight Consolidation

Collaborative Distillation for Ultra-Resolution Universal Style Transfer

Rethinking and Improving the Robustness of Image Style Transfer

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Content-Aware GAN Compression

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Collaging Class-Specific GANs for Semantic Image Synthesis

3D-FM GAN: Towards 3D-Controllable Face Manipulation

IMAGINE: Image Synthesis by Image-Guided Model Inversion

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Generative Video Propagation

Generative Image Layer Decomposition with Visual Effects

Modeling Artistic Workflows for Image Generation and Editing

TransPixeler: Advancing Text-to-Video Generation with Transparency

X-Fusion: Introducing New Modality to Frozen Large Language Models

Contrastive Learning for Diverse Disentangled Foreground Generation

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

The Causal Impact of Credit Lines on Spending Distributions

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data

Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification

Cross-modal Latent Space Alignment for Image to Avatar Translation

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying

papers (23)

Few-Shot Image Generation via Cross-Domain Correspondence

Few-shot Image Generation with Elastic Weight Consolidation

Collaborative Distillation for Ultra-Resolution Universal Style Transfer

Rethinking and Improving the Robustness of Image Style Transfer

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

Content-Aware GAN Compression

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing

Collaging Class-Specific GANs for Semantic Image Synthesis

3D-FM GAN: Towards 3D-Controllable Face Manipulation

IMAGINE: Image Synthesis by Image-Guided Model Inversion

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Generative Video Propagation

Generative Image Layer Decomposition with Visual Effects

Modeling Artistic Workflows for Image Generation and Editing

TransPixeler: Advancing Text-to-Video Generation with Transparency

X-Fusion: Introducing New Modality to Frozen Large Language Models

Contrastive Learning for Diverse Disentangled Foreground Generation

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

The Causal Impact of Credit Lines on Spending Distributions

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data

Scene Graph Guided Generation: Enable Accurate Relations Generation in Text-to-Image Models via Textural Rectification

Cross-modal Latent Space Alignment for Image to Avatar Translation

MAGICK: A Large-scale Captioned Dataset from Matting Generated Images using Chroma Keying