@article{augmentingattentionwithexponentiallydeca, title = {Augmenting Attention with Exponentially Decaying Memory Improves Query-Aware KV Sparsity}, author = {Xiuying Wei and Caglar Gulcehre}, year = {2026}, eprint = {2605.28640}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.28640}, }