We are aiming to make progress on some of the hardest scientific challenges around the deployment of robots in unstructured environments, by leveraging data from different sources and modalities, and learning transferable priors grounded in physical properties found in the real-world. Publication or desire to publish at high-impact conferences/journals (e.g., CoRL, ICLR, NeurIPS, CVPR, ICCV, ECCV, ICML, UAI, AISTATS, AAAI, TMLR, RSS, ICRA, IROS, RA-L, etc.) on some of the aforementioned topics.