@article{catscontextuallyawarethresholdingfor, title = {CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models}, author = {DongHyun Lee and Je-Yong Lee and Genghan Zhang and Mo Tiwari and Azalia Mirhoseini}, year = {2024}, eprint = {2404.08763}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.08763v4}, }