@article{livemindlowlatencylargelanguagemodels, title = {LiveMind: Low-latency Large Language Models with Simultaneous Inference}, author = {Chuangtao Chen and Grace Li Zhang and Xunzhao Yin and Cheng Zhuo and Ulf Schlichtmann and Bing Li}, year = {2024}, eprint = {2406.14319}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.14319v2}, }