Acknowledgements.md

TiagoGym:

@article{dass2024telemoma,
  title={TeleMoMa: A Modular and Versatile Teleoperation System for Mobile Manipulation},
  author={Dass, Shivin and Ai, Wensi and Jiang, Yuqian and Singh, Samik and Hu, Jiaheng and Zhang, Ruohan and Stone, Peter and Abbatematteo, Ben and Martín-Martín, Roberto},
  journal={arXiv preprint arXiv:2403.07869},
  year={2024}
}

GSAM Wrapper:

@article{zhu2024orion,
  title={Vision-based Manipulation from Single Human Video with Open-World Object Graphs},
  author={Zhu, Yifeng and Lim, Arisrei and Stone, Peter and Zhu, Yuke},
  journal={arXiv preprint arXiv:2405.20321},
  year={2024}
}

Set-of-Marker Prompting:

@article{nasiriany2024pivot,
  title={Pivot: Iterative visual prompting elicits actionable knowledge for vlms},
  author={Nasiriany, Soroush and Xia, Fei and Yu, Wenhao and Xiao, Ted and Liang, Jacky and Dasgupta, Ishita and Xie, Annie and Driess, Danny and Wahid, Ayzaan and Xu, Zhuo and others},
  journal={arXiv preprint arXiv:2402.07872},
  year={2024}
}

Parts of the code are borrowed from the Behavior 1K, like pickup primitive, transforms.

@article{li2024behavior,
  title={Behavior-1k: A human-centered, embodied ai benchmark with 1,000 everyday activities and realistic simulation},
  author={Li, Chengshu and Zhang, Ruohan and Wong, Josiah and Gokmen, Cem and Srivastava, Sanjana and Mart{\'\i}n-Mart{\'\i}n, Roberto and Wang, Chen and Levine, Gabrael and Ai, Wensi and Martinez, Benjamin and others},
  journal={arXiv preprint arXiv:2403.09227},
  year={2024}
}