@article{trainabledynamicmasksparseattention, title = {Trainable Dynamic Mask Sparse Attention}, author = {Jingze Shi and Yifan Wu and Yiran Peng and Bingheng Wu and Liangdong Wang and Guang Liu and Yuyu Luo}, year = {2025}, eprint = {2508.02124}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.02124}, }