@article{mtrainingdistributeddynamicsparseattenti, title = {MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training}, author = {Wenxuan Li and Chengruidong Zhang and Huiqiang Jiang and Yucheng Li and Yuqing Yang and Lili Qiu}, year = {2025}, eprint = {2510.18830}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.18830}, }