@misc{allshire2025visual, title={Visual Imitation Enables Contextual Humanoid Control}, author={Arthur Allshire and Hongsuk Choi and Junyi Zhang and David McAllister and Anthony Zhang and Chung Min Kim and Trevor Darrell and Pieter Abbeel and Jitendra Malik and Angjoo Kanazawa}, year={2025}, eprint={2505.03729}, archivePrefix={arXiv}, primaryClass={cs.RO}, url={https://arxiv.org/abs/2505.03729} }