@article{250605249,
  title = {On the Convergence of Gradient Descent on Learning Transformers with Residual Connections},
  author = {Zhen Qin and Jinxin Zhou and Zhihui Zhu},
  year = {2025},
  eprint = {2506.05249},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.05249v1},
}