Yijun Li

Research Scientist

Seattle

Yijun joined Adobe Research in June 2019, working in the areas of computer vision, computational photography, and machine learning.

He obtained the Ph.D. degree at University of California, Merced, working with Prof. Ming-Hsuan Yang. Before that, he received the M.S. degree at Shanghai Jiao Tong University and B.S. degree at Zhejiang University.

His research to date focuses on visual synthesis for natural image and video editing. The goal is to develop effective computational models to facilitate more realistic and stunning creations, which will bring brand new user experiences and transform the ways we communicate and collaborate. He has been supported by Facebook Fellowship (2019), Adobe Fellowship (2018), and Snap Fellowship (2017). For more information, please visit his personal homepage.

Publications

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment

Li, Y., Liu, H., Cai, M., Li, Y., Shechtman, E., Lin, Z., Lee, Y., Singh, K. (Sep. 30, 2024)

European Conference on Computer Vision (ECCV'24)

Separate-and-Enhance: Compositional Finetuning for Text-to-Image Diffusion Models

Bao, Z., Li, Y., Singh, K., Wang, Y., Hebert, M. (Jul. 27, 2024)

SIGGRAPH 2024

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

Burgert, R., Price, B., Kuen, J., Li, Y., Ryoo, M. (Jun. 19, 2024)

CVPR 2024

AT-EDM: Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models

Wang, H., Liu, D., Kang, Y., Li, Y., Lin, Z., Jha, N., Liu, Y. (Jun. 17, 2024)

CVPR 2024

Contrastive Learning for Diverse Disentangled Foreground Generation

Li, Y., Li, Y., Lu, J., Shechtman, E., Lee, Y., Singh, K. (Oct. 23, 2022)

European Conference on Computer Vision (ECCV'22)

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

Liu, Y., Shu, Z., Li, Y., Lin, Z., Zhang, R., Kung, S. (Oct. 23, 2022)

European Conference on Computer Vision (ECCV)

Inverting and Editing Real Images with Spatially Varying and Automatic Latent Selection

Parmar, G., Li, Y., Lu, J., Zhang, R., Zhu, J., Singh, K. (Jun. 19, 2022)

CVPR2022

Collaging Class-specific GANs for Semantic Image Synthesis

Li, Y., Li, Y., Lu, J., Shechtman, E., Lee, Y., Singh, K., Lu, J. (Oct. 13, 2021)

International Conference on Computer Vision (ICCV'21)

Few-shot Image Generation via Cross-domain Correspondence

Ojha, U., Li, Y., Lu, J., Efros, A., Lee, Y., Shechtman, E., Zhang, R. (Jun. 23, 2021)

Computer Vision and Pattern Recognition (CVPR'21)

IMAGINE: Image Synthesis by Image-Guided Model Inversion

Wang, P., Li, Y., Singh, K., Lu, J., Vasconcelos, N. (Jun. 19, 2021)

CVPR2021

Content-Aware GAN Compression

Liu, Y., Shu, Z., Li, Y., Lin, Z., Perazzi, F., Kung, S. (Jun. 19, 2021)

Conference on Computer Vision and Pattern Recognition (CVPR)

Few-shot Image Generation via Self-adaptation

Li, Y., Zhang, R., Lu, J., Shechtman, E. (Dec. 6, 2020)

Neurips 2020

Modeling Artistic Workflows for Image Generation and Editing

Tseng, H., Fisher, M., Lu, J., Li, Y., Kim, V., Yang, M., Lu, J. (Aug. 23, 2020)

16th European conference on computer vision (ECCV2020)