Wojciech Galuba

visual question answering (2) embodied ai (2) multimodal learning (2) reinforcement learning (1) benchmark evaluation (1) transfer learning (1) self-supervised learning (1) data augmentation (1) cross-modal learning (1) multi-modal learning (1) object goal navigation (1) scene text detection (1) audio classification (1) vision language model (1) cross-modal alignment (1) foundation model (1) adversarial example (1) masked autoencoder (1) physics simulation (1) human evaluation (1)