@inproceedings{xie-etal-2026-aura, title = "{AURA}-{KV}: Adaptive Subspace Rank Approximation for Efficient Long-Context {LLM} Inference", author = "Xie, Jincheng and Shi, Hao and Jiang, Zhengyi and Huang, Zhongyi and Song, Linqi and Hou, Hanxu", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.2250/", pages = "51179--51203", ISBN = "979-8-89176-459-0" }