@inproceedings{TrainCheckOSDI2025,
author = {Jiang, Yuxuan and Zhou, Ziming and Xu, Boyu and Liu, Beijie and Xu, Runhui and Huang, Peng},
title = {Training with Confidence: Catching Silent Errors in Deep Learning Training with Automated Proactive Checks},
booktitle = {Proceedings of the 19th USENIX Symposium on Operating Systems Design and Implementation},
series = {OSDI '25},
month = {July},
year = {2025},
address = {Boston, MA, USA},
publisher = {USENIX Association},
}