@misc{dl2-19-1,
  title={Adaptive Computation Time for Recurrent Neural Networks},
  author={Alex Graves},
  year={2016},
  url={https://arxiv.org/abs/1603.08983v6}
}
@misc{dl2-19-2,
  title={BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks},
  author={Surat Teerapittayanon, Bradley McDanel, H.T. Kung},
  year={2017},
  url={https://arxiv.org/abs/1709.01686v1}
}
@misc{dl2-19-3,
  title={Multi-Scale Dense Networks for Resource Efficient Image Classification},
  author={Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger},
  year={2018},
  url={https://arxiv.org/abs/1703.09844v5}
}
@misc{dl2-19-4,
  title={Shallow-Deep Networks: Understanding and Mitigating Network Overthinking},
  author={Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras},
  year={2019},
  url={https://arxiv.org/abs/1810.07052v3}
}
@misc{dl2-19-5,
  title={PonderNet: Learning to Ponder},
  author={Andrea Banino, Jan Balaguer, Charles Blundell},
  year={2021},
  url={https://arxiv.org/abs/2107.05407v2}
}
@misc{dl2-19-6,
  title={DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference},
  author={Ji Xin, Raphael Tang, Jaejun Lee, Yaoliang Yu, Jimmy Lin},
  year={2020},
  url={https://arxiv.org/abs/2004.12993v1}
}