Fengda Zhu

vision-language navigation (6) reinforcement learning (3) embodied agent (2) self-supervised learning (2) data augmentation (2) imitation learning (1) image generation (1) contrastive learning (1) domain adaptation (1) transfer learning (1) scene understanding (1) video generation (1) adversarial learning (1) visual navigation (1) policy learning (1) cross-modal learning (1) domain generalization (1) agent navigation (1) text-to-image generation (1) representation learning (1)