@article{generalizationandscalinglawsformixtureof, title = {Generalization and Scaling Laws for Mixture-of-Experts Transformers}, author = {Mansour Zoubeirou a Mayaki}, year = {2026}, eprint = {2604.09175}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.09175}, }