@article{diversityoftransformerlayersoneaspectof, title = {Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws}, author = {Hidetaka Kamigaito and Ying Zhang and Jingun Kwon and Katsuhiko Hayashi and Manabu Okumura and Taro Watanabe}, year = {2025}, eprint = {2505.24009}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24009v1}, }