Xiangyang Zhu

few-shot learning (3) diffusion transformer (2) multimodal learning (2) text-to-image generation (2) transfer learning (1) domain adaptation (1) zero-shot learning (1) multimodal large language model (1) image captioning (1) privacy preservation (1) 3d segmentation (1) neural network optimization (1) out-of-distribution generalization (1) scene segmentation (1) large multimodal model (1) diffusion model (1) object detection (1) differentiable rendering (1) image segmentation (1) reinforcement learning (1)