Xiaoyi Dong

vision-language model (7) multimodal learning (6) adversarial attack (6) vision transformer (5) large language model (4) video understanding (4) adversarial perturbation (3) image classification (3) object detection (3) adversarial sample (3) large vision-language model (3) point cloud (3) multi-modal learning (3) multimodal large language model (3) transfer learning (2) diffusion model (2) instruction tuning (2) vision language model (2) few-shot learning (2) reinforcement learning (2)