I'm interested in developing embodied AI systems capable of helping us in the humdrum of everyday activities within messy rooms, offices, and kitchens, in a reliable, compliant, and scalable manner without requiring significant robot-specific data collection and task-specific heuristics. To this end, I have worked on learning goal-conditioned manipulation from human videos, exploration for robot learning, and improving efficiency through semantic augmentations and novel policy architectures. I have eclectic research interests, and have also worked on robustness in machine learning, and improving sample efficiency, scalability, and representations in reinforcement learning.