Yuchen Liu

Research Engineer

San Jose

Yuchen joined Adobe Research as a Research Engineer in 2022. His research interest spans generative modeling, 3D reconstruction, and efficient deep learning. More specifically, he’s interested in building low-cost deep image generator with less storage and faster inference for applications like image synthesis and image editing with considerable controllability. His prior works provide an order of magnitude complexity reduction from GANs and enable precise 3D controllability for GAN-based face synthesis.

Yuchen obtained his Ph.D. from Princeton University and his B.Eng at HKUST. Check out more about Yuchen at his personal webpage.

Publications

Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection

Ganjdanesh, A., Kang, Y., Liu, Y., Zhang, R., Lin, Z., Huang, H. (Oct. 1, 2024)

European Conference on Computer Vision (ECCV)

Personalized Residuals for Concept-Driven Text-to-Image Generation

Ham, C., Fisher, M., Hays, J., Kolkin, N., Liu, Y., Zhang, R., Hinz, T. (Jun. 19, 2024)

CVPR 2024

SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model

Li, Z., Kang, Y., Liu, Y., Liu, D., Hinz, T., Liu, F., Wang, Y. (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

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)

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)