Difan Liu

Research Scientist, Adobe Systems

Joined

November 2019

Names

Difan Liu (Preferred)

Emails

****@cs.umass.edu (Confirmed)

****@umass.edu (Confirmed)

****@adobe.com (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Research Scientist

Adobe Systems (adobe.com)

2022 – Present

PhD student

Department of Computer Science, University of Massachusetts, Amherst (cs.umass.edu)

2017 – 2022

Advisors, Relations & Conflicts

Coauthor

Matthew Fisher

2020 – Present

PhD Advisor

Evangelos Kalogerakis

2017 – 2022

Expertise

computer graphics

computer vision

machine learning

2017 – Present

Publications

Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation
Yuan Yao, Yicong Hong, Difan Liu, Long Mai, Feng Liu, Jiebo Luo
- OpenReview Archive Direct Upload
- Readers: Everyone
VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation
Shoubin Yu, Difan Liu, Ziqiao Ma, Yicong Hong, Yang Zhou, Hao Tan, Joyce Chai, Mohit Bansal
- ICCV 2025
- Readers: Everyone
Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation
Subin Kim, Sangwoo Mo, Mamshad Nayeem Rizve, Yiran Xu, Difan Liu, Jinwoo Shin, Tobias Hinz
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Rethinking Layered Graphic Design Generation with a Top-Down Approach
Jingye Chen, Zhaowen Wang, Nanxuan Zhao, Li Zhang, Difan Liu, Jimei Yang, Qifeng Chen
- CoRR 2025
- Readers: Everyone
Progressive Autoregressive Video Diffusion Models
Desai Xie, Zhan Xu, Yicong Hong, Hao Tan, Difan Liu, Feng Liu, Arie Kaufman, Yang Zhou
- CVPR 2025
- Readers: Everyone
VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation
Shoubin Yu, Difan Liu, Ziqiao Ma, Yicong Hong, Yang Zhou, Hao Tan, Joyce Chai, Mohit Bansal
- CoRR 2025
- Readers: Everyone
Visual Persona: Foundation Model for Full-Body Human Customization
Jisu Nam, Soowon Son, Zhan Xu, Jing Shi, Difan Liu, Feng Liu, Aashish Misraa, Seungryong Kim, Yang Zhou
- CoRR 2025
- Readers: Everyone
Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
Hongjie Wang, Difan Liu, Yan Kang, Yijun Li, Zhe Lin, Niraj Jha, Yuchen Liu
- CVPR2024
- Readers: Everyone
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
Zihan Ding, Chi Jin, Difan Liu, Haitian Zheng, Krishna Kumar Singh, Qiang Zhang, Yan Kang, Zhe Lin, Yuchen Liu
- OpenReview Archive Direct Upload
- Readers: Everyone
Mean-Shift Distillation for Diffusion Mode Seeking
Vikas Thamizharasan, Nikitas Chatzis, Iliyan Georgiev, Matthew Fisher, Difan Liu, Nanxuan Zhao, Evangelos Kalogerakis, Michal Lukáč
- Submitted to ICML 2025
- Readers: Everyone

View all 33 publications

Co-Authors

View all 94 co-authors