@article{activationawareprobequeryeffectivekey, title = {Activation-aware Probe-Query: Effective Key-Value Retrieval for Long-Context LLMs Inference}, author = {Qingfa Xiao and Jiachuan Wang and Haoyang Li and Cheng Deng and Jiaqi Tang and Shuangyin Li and Yongqi Zhang and Jun Wang and Lei Chen}, year = {2025}, eprint = {2502.13542}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.13542v1}, }