Haotian Liu

vision-language model (5) visual question answering (4) multimodal learning (4) large language model (3) large multimodal model (3) few-shot learning (3) multimodal large language model (2) zero-shot learning (2) industrial anomaly (2) transfer learning (2) visual instruction tuning (2) anomaly detection (2) industrial anomaly detection (2) instruction following (2) image generation (2) object detection (2) curriculum learning (1) pose estimation (1) domain adaptation (1) vision transformer (1)