@article{practicalefficiencyofmuonforpretraining,
  title = {Practical Efficiency of Muon for Pretraining},
  author = {Essential AI and : and Ishaan Shah and Anthony M. Polloreno and Karl Stratos and Philip Monk and Adarsh Chaluvaraju and Andrew Hojel and Andrew Ma and Anil Thomas and Ashish Tanwer and Darsh J Shah and Khoi Nguyen and Kurt Smith and Michael Callahan and Michael Pust and Mohit Parmar and Peter Rushton and Platon Mazarakis and Ritvik Kapila and Saurabh Srivastava and Somanshu Singla and Tim Romanski and Yash Vanjani and Ashish Vaswani},
  year = {2025},
  eprint = {2505.02222},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.02222v4},
}