作者:Yi Li, Yuquan Deng, Jesse Zhang, Joel Jang, Marius Memmel, Raymond Yu, Caelan Reed Garrett, Fabio Ramos, Dieter Fox, Anqi Li, Abhishek Gupta, Ankit Goyal · 单位:NVIDIA, University of Washington, University of Southern California · 会议/期刊:arXiv preprint · 方向:层级系统 / 数据高效预训练 · 发布日期:2025-02-08