Arjun Majumdar

visual reasoning (2) multimodal learning (2) zero-shot learning (2) sim-to-real transfer (1) visual question answering (1) vision-language navigation (1) offline reinforcement learning (1) domain adaptation (1) scene understanding (1) object detection (1) trajectory prediction (1) sequential decision making (1) self-supervised learning (1) robot navigation (1) vision transformer (1) 3d reconstruction (1) visual navigation (1) object localization (1) visual representation (1) representation learning (1)