@article{twofailuremodesofdeeptransformersand, title = {Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation}, author = {Alessio Giorlandino and Sebastian Goldt}, year = {2025}, eprint = {2505.24333}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24333v1}, }