Xijun Wang

image generation (2) hallucination detection (2) vision-language model (2) multimodal learning (2) model compression (2) face recognition (2) diffusion model (2) image restoration (1) text-to-image synthesis (1) semantic segmentation (1) self-supervised learning (1) knowledge distillation (1) data augmentation (1) video recognition (1) metric learning (1) neural network optimization (1) visual reasoning (1) visual question answering (1) efficient computing (1) point cloud (1)