@article{JMLR:v27:24-0169,
  author  = {Yueyao Yu and Yin Zhang},
  title   = {Why "Classic" Transformers Are Shallow and A Depth-Enabling Technique},
  journal = {Journal of Machine Learning Research},
  year    = {2026},
  volume  = {27},
  number  = {64},
  pages   = {1--32},
  url     = {http://jmlr.org/papers/v27/24-0169.html}
}