@article{vaswani2017attention,
  title={Attention is All you Need},
  author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
  journal={Advances in neural information processing systems},
  volume={30},
  year={2017},
  url={https://arxiv.org/abs/1706.03762},
  eprint={1706.03762}
}

@article{devlin2018bert,
  title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1810.04805},
  year={2018},
  eprint={1810.04805}
}

@inproceedings{brown2020language,
  title={Language models are few-shot learners},
  author={Brown, Tom and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared D and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
  booktitle={Advances in Neural Information Processing Systems},
  volume={33},
  pages={1877--1901},
  year={2020},
  url={https://arxiv.org/abs/2005.14165}
}

@article{fake2023paper,
  title={This is a Fake Paper That Does Not Exist},
  author={Nobody, John and Doesnotexist, Jane},
  journal={Fake Journal},
  year={2023},
  url={https://example.com/nonexistent}
}


@article{Briani2007,
author = {Briani, M. and  Natalini, R. and Russo, G.},
title = {{I}mplicit–{E}xplicit numerical schemes for jump–diffusion processes},
journal = {Calcolo},
vol = {44},
pages = {33--57},
year = {2007},
doi={10.1007/s10092-007-0128-0},
}