HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
arXiv:2603.10067v1 Announce Type: new Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We …
Tianyu Pang, Yujie Fang, Zihang Liu, Shenyang Deng, Lei Hsiung, Shuhua Yu, Yaoqing Yang
조회수 35회