Jingkang Yang

multimodal learning (4) panoptic segmentation (3) transfer learning (2) large multimodal model (2) multimodal large language model (2) 4d scene understanding (2) video understanding (2) temporal modeling (2) scene graph generation (2) scene graph (2) benchmark evaluation (2) object detection (2) zero-shot learning (2) large language model (2) visual reasoning (2) question answering (2) domain generalization (2) out-of-distribution detection (2) direct preference optimization (1) visual question answering (1)