Xiaoyue Duan

vision-language model (3) vision language model (3) diffusion model (3) feature extraction (2) image editing (2) cross-modal learning (1) intellectual property (1) catastrophic forgetting (1) feature correlation (1) earth mover distance (1) image generation (1) video understanding (1) distribution alignment (1) generative adversarial network (1) multi-modal learning (1) few-shot learning (1) ddim inversion (1) prompt tuning (1) continual learning (1) reinforcement learning (1)