@article{
wang2026scaling,
title={Scaling Large Language Models with Fully Sparse Activations},
author={Hongyu Wang and Shuming Ma and Ruiping Wang and Furu Wei},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=MntjMCroiE},
note={}
}