Xiaoshi Wu

text-to-image generation (3) foundation model (2) human preference (2) diffusion model (2) vision language model (2) preference learning (1) visual question answering (1) transfer learning (1) multi-modal learning (1) open-vocabulary detection (1) model alignment (1) weakly-supervised learning (1) preference modeling (1) image captioning (1) multimodal learning (1) object detection (1) vision-language model (1) model fine-tuning (1) multimodal reasoning (1) few-shot learning (1)