I am a researcher at Adobe Research where I research in image generative models and efficient deep learning (CV). Before that, I got my Ph.D. in the Department of Electrical and Computer Engineering at Princeton University in Novemeber 2022, fortunately supervised by Prof. Sun-Yuan Kung and Prof. David Wentzlaff. I received my BEng in Electronic and Computer Engineering from Hong Kong University of Science and Technology (HKUST) in June 2017.

I spent two wonderful summers at Adobe Research working with Dr. Zhixin Shu, Dr. Yijun Li, Dr. Zhe Lin, Dr. Richard Zhang, and Dr. Federico Perazzi in 2020 and 2021. Adobe Research is open to university collaboration in forms of internship and joint projects for motivated students. If you are interested in doing research projects with me, please drop me an email with your CV.

Publication

• Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
  Hongjie Wang, Difan Liu, Yan Kang, Yijun Li, Zhe Lin, Niraj Jha, Yuchen Liu
  To appear in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).


• SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model
  Zhengang Li, Yan Kang, Yuchen Liu, Difan Liu, Tobias Hinz, Feng Liu, Yanzhi Wang
  To appear in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).


• Personalized Residuals for Concept-Driven Text-to-Image Generation
  Cusuh Ham, Matthew Fisher, James Hays, Nicholas Kolkin, Yuchen Liu, Richard Zhang, Tobias Hinz
  To appear in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).


• Building Efficient Neural Prefetcher
  Yuchen Liu, Georgios Tziantzioulis, David Wentzlaff
  International Symposium on Memory Systems (MEMSYS 2023).
  (paper)


• 3D-FM GAN: Towards 3D-Controllable Face Manipulation
  Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Richard Zhang, and S.Y. Kung
  European Conference on Computer Vision (ECCV 2022).
  (paper) (arxiv) (code) (webpage) (video) (poster)


• Evolving Transferable Neural Pruning Functions
  Yuchen Liu, S.Y. Kung, and David Wentzlaff
  Genetic and Evolutionary Computation Conference (GECCO 2022).
  (paper) (arxiv) (code)
  


• Class-Discriminative CNN Compression
  Yuchen Liu, David Wentzlaff, and S.Y. Kung
  International Conference on Pattern Recognition (ICPR 2022).
  (paper) (code)
  


• Content-Aware GAN Compression
  Yuchen Liu, Zhixin Shu, Yijun Li, Zhe Lin, Federico Perazzi, and S.Y. Kung
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021).
  (paper) (arxiv) (webpage) (code)
  


• Rethinking Class-Discrimination Based CNN Channel Pruning
  Yuchen Liu, David Wentzlaff, and S.Y. Kung
  arXiv preprint arXiv:2004.14492 (2020).
  (paper)
  


• Methodical Design and Trimming of Deep Learning Networks: Enhancing External BP Learning with Internal Omnipresent-supervision Training Paradigm
  S.Y. Kung, Zejiang Hou, and Yuchen Liu
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019).
  (paper)


• Extracting gait velocity and stride length from surrounding radio signals
  Chen-Yu Hsu, Yuchen Liu, Zachary Kabelac, Rumen Hristov, Dina Katabi, Christine Liu
  ACM Conference on Human Factors in Computing Systems (CHI 2017).
  (paper)

Service

• Conference Reviewer/Program Committee
  • CVPR - 2021, 2023, 2024
  • NeurIPS - 2021, 2022, 2023
  • ICML - 2022, 2023, 2024
  • WACV - 2023, 2024
  • AAAI - 2023, 2024
• Journal Reviewer
  • ACM Computing Surveys

Awards and Honors

• HKUST Outstanding Undergraduate - HKUST, Hong Kong, May 2017
  Awareded to top 3% of graduating undergraduate students
• The 14th National Challenge Cup, National Round, Third Prize - HKUST, Hong Kong, October 2015
  Innovation competition joined by more than 2.5 million students from over 3,000 institutions
• Scholarship Scheme for Continuing Undergraduate Students - HKUST, Hong Kong, 2013 - 2017
  Awarded to the top 5% of undergraduate students
• Dean's List - HKUST, Hong Kong, 2014 - 2017
  Acknowledgement from HKUST's dean to students with excellent academic performance