Jing Shi

multimodal learning (4) large language model (4) speech separation (4) image editing (3) attention mechanism (3) diffusion model (3) weakly supervised learning (3) image generation (3) sequence-to-sequence model (3) visual question answering (2) zero-shot learning (2) scene graph generation (2) generative adversarial network (2) text-to-image generation (2) representation learning (2) image captioning (2) personalized generation (2) self-supervised learning (2) knowledge distillation (2) contrastive learning (2)