Mengxue Qu

object detection (2) image segmentation (1) few-shot learning (1) scene understanding (1) direct preference optimization (1) weakly supervised learning (1) preference optimization (1) multi-modal learning (1) intention understanding (1) benchmark dataset (1) vision-language model (1) supervised fine-tuning (1) large vision-language model (1) adversarial sample (1) affordance understanding (1) bounding box annotation (1) confirmation bia (1) pixel-level annotation (1) object affordance (1) referring expression segmentation (1)