2 citations · 3 across the 4 of their papers we have counts for
4 papers
Towards Robustness and Diversity: Continual Learning in Dialog Generation with Text-Mixup and Batch Nuclear-Norm Maximization
Zihan Wang, Jiayu Xiao, Mengxiang Li +4
In our dynamic world where data arrives in a continuous stream, continual learning enables us to incrementally add new tasks/domains without the need to retrain from scratch. A maj…
Pick-and-Draw: Training-free Semantic Guidance for Text-to-Image Personalization
Henglei Lv, Jiayu Xiao, Liang Li +1
Diffusion-based text-to-image personalization have achieved great success in generating subjects specified by users among various contexts. Even though, existing finetuning-based m…
R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
Jiayu Xiao, Henglei Lv, Liang Li +2
Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey ap…
Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment
Jiayu Xiao, Liang Li, Chaofei Wang +2
Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domai…