Yufan Zhou
Research Scientist at Adobe Research
Email: yufanzho AT buffalo DOT eduBio
Currently my research focuses on generative models. More specifically, I'm interested in:
- Multi-modal generative models (assistants) which are more user-friendly;
- Customizing pre-trained generative models;
- Saving the training or dataset construction cost in generative modeling;
I obtained my Ph.D. from the Department of Computer Science and Engineering, University at Buffalo, under the supervision of
Prof. Jinhui Xu and
Prof. Changyou Chen.
I received my B.E. degree from Zhejiang University.
I worked as a Research Intern with Chunyuan Li (Microsoft), Ruiyi Zhang (Adobe), Bingchen Liu (ByteDance).
If you have interest in interning at Adobe, feel free to send me an email with your CV and a short overview of the topics that interest you.
Selected Papers [More]
-
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.An assistant which can generate creative images for specific user-input subject along with text explanation and elaboration in 2-5 seconds, without any fine-tuning.
-
A novel framework for customized text-to-image generation without the use of regularization.
We can efficiently customize a large-scale text-to-image generation model on single GPU, with only one image provided by the user. -
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023.We propose a method termed Corgi, which can better generate image embeddings from text inside multimodal embedding space.
It benefits both standard and language-free text-to-image generation. And yes, I do have a Corgi. -
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.Our proposed work, Lafite, is the first work which can successfully train text-to-image generation model with image-only dataset.
-
AAAI conference on Artificial Intelligence (AAAI), 2022.
-
International Conference on Learning Representations (ICLR), 2021.
-
Conference on Neural Information Processing Systems (NeurIPS), 2020.
Professional Service
- Conferences Program Committee/Reviewer: NeurIPS 2020, 2021, 2022, 2023; ICML 2021, 2022, 2023, 2024; ICLR 2022, 2023, 2024; CVPR 2023, 2024; AISTATS 2021; AAAI 2021, 2022; IJCAI 2021; EMNLP 2022, 2023; ECCV 2024; ACL 2023;
- Journal Reviewer: IEEE Transactions on Neural Networks and learning systems; IEEE Transactions on Circuits and Systems for Video Technology;