Zhilong Ji

large language model (4) vision-language model (3) image generation (2) customized generation (2) mathematical reasoning (2) data augmentation (2) generative adversarial network (2) text-to-image generation (2) diffusion model (2) multimodal learning (2) scene text detection (2) few-shot learning (2) knowledge distillation (1) attention mechanism (1) catastrophic forgetting (1) style transfer (1) multi-label classification (1) domain adaptation (1) benchmark evaluation (1) syntax parsing (1)