Yuxiang Wei

image generation (5) diffusion model (4) semantic image synthesis (3) text-to-image generation (3) large language model (2) customized generation (2) text-to-image model (2) feature fusion (2) text-to-image diffusion (2) vision-language model (2) parameter-efficient fine-tuning (2) video generation (2) knowledge distillation (2) multimodal learning (2) domain adaptation (2) code generation (2) instruction tuning (2) generative adversarial network (2) black-box optimization (1) self-supervised learning (1)