Yicong Hong

vision-language navigation (7) vision-and-language navigation (5) multi-modal learning (4) embodied ai (3) imitation learning (2) instruction following (2) agent system (2) multimodal learning (2) visual navigation (2) sim-to-real transfer (1) video generation (1) object detection (1) attention mechanism (1) data augmentation (1) contrastive learning (1) scene understanding (1) transfer learning (1) multi-task learning (1) trajectory prediction (1) cross-modal learning (1)