Quang Nguyen

Disentangling content and style from single images via visual autoregressive modeling for improved recontextualization and stylization.

Instantly text-guided image editing within a fraction of second by one-step diffusion model

Synthesizing semantic segmentation datasets by utilizing cross-attention and self-attention maps of Stable Diffusion

Integrating the SIRD compartmental model into a Variational Autoencoder (VAE) framework, this approach enhances pandemic forecasting by combining accurate predictions with improved explainability