Back to papers
September 1, 2026cs.LG

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu, Shaofan Liu, Jiaheng Liu, Wenhao Huang, Shen Yan, Jian Li
Read on arXivDownload PDF
HF Upvotes

84

Categories

cs.LG

SMELT: Scaling Laws for Compute-Matched MoE | One9Founders