@article{whenandwhygroupingattentionheadsaccelera, title = {When and Why Grouping Attention Heads Accelerates Muon Optimization}, author = {Hongtao Zhang and Wenjie Zhou and Wei Chen and Xueqi Cheng}, year = {2026}, eprint = {2605.08933}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.08933}, }