Scholar
Yuchen Liu
Google Scholar ID: yYGI_XsAAAAJ
Adobe Research
Citations & Impact
Citations
298
H-index
8
i10-index
7
Publications
17
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- X-Fusion: Introducing New Modality to Frozen Large Language Models, Best Paper of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop of Transformer for Vision (CVPRW 2025).
- ZipIR: Latent Pyramid Diffusion Transformer for High-Resolution Image Restoration, arXiv preprint arXiv:2504.08591 (2025).
- Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks, arXiv preprint arXiv:2503.17539 (2025).
- DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization, arXiv preprint arXiv:2412.15689 (2024).
- Mixture of efficient diffusion experts through automatic interval and sub-network selection, European Conference on Computer Vision (ECCV 2024).
- Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).
- SNED: Superposition Network Architecture Search for Efficient Video Diffusion Model, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).
- Personalized Residuals for Concept-Driven Text-to-Image Generation, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).
Research Experience
- Adobe Research, San Jose, CA: Research Scientist/Engineer II, July 2024 - Present; Research Scientist/Engineer I, December 2022 - July 2024.
- Adobe Research, San Jose, CA: Research Intern, May - November 2021, Mentor: Dr. Zhixin Shu.
- Adobe Research, San Francisco, CA: Research Intern, May - November 2020, Mentors: Dr. Federico Perazzi and Dr. Zhixin Shu.
- Princeton University, Princeton, NJ: Research Assistant, September 2017 - November 2022, Advisors: Prof. Sun-Yuan Kung and Prof. David Wentzlaff.
- Massachusetts Institute of Technology, Cambridge, MA: Research Intern, June - August 2016, Advisor: Prof. Dina Katabi.
Background
- Research interests: visual generative modeling, particularly in few-step generation approaches to address the iterative nature of diffusion models. Currently a researcher at Adobe Research.
Miscellany
- No specific hobbies or interests mentioned.
