@inproceedings{theshapedtransformerattentionmodelsin,
  title = {The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit},
  author = {Lorenzo Noci and Chuning Li and Mufan Bill Li and Bobby He and Thomas Hofmann and Chris Maddison and Daniel M. Roy},
  year = {2023},
  booktitle = {NeurIPS 2023 11},
  eprint = {2306.17759},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.17759v2},
}