@article{scalingembeddinglayersinlanguagemodels, title = {Scaling Embedding Layers in Language Models}, author = {Da Yu and Edith Cohen and Badih Ghazi and Yangsibo Huang and Pritish Kamath and Ravi Kumar and Daogao Liu and Chiyuan Zhang}, year = {2025}, eprint = {2502.01637}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.01637v2}, }