@article{salelowbitestimationforefficientsparse, title = {SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling}, author = {Xiaodong Ji and Hailin Zhang and Fangcheng Fu and Bin Cui}, year = {2025}, eprint = {2505.24179}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24179v1}, }