@article{exploringthebenefitofactivationsparsity, title = {Exploring the Benefit of Activation Sparsity in Pre-training}, author = {Zhengyan Zhang and Chaojun Xiao and Qiujieli Qin and Yankai Lin and Zhiyuan Zeng and Xu Han and Zhiyuan Liu and Ruobing Xie and Maosong Sun and Jie zhou}, year = {2024}, eprint = {2410.03440}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.03440v1}, }