@article{hylrahybridlayerreuseattentionforefficie, title = {HyLRA: Hybrid Layer Reuse Attention for Efficient Long-Context Inference}, author = {Xuan Ai and Qingqing Yang and Peng Wang and Lei Deng and Lin Zhang and Renhai Chen and Gong Zhang}, year = {2026}, eprint = {2602.00777}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2602.00777}, }