@article{scalinginferenceefficientlanguagemodels, title = {Scaling Inference-Efficient Language Models}, author = {Song Bian and Minghao Yan and Shivaram Venkataraman}, year = {2025}, eprint = {2501.18107}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.18107v1}, }