@article{inferencetimehyperscalingwithkvcache, title = {Inference-Time Hyper-Scaling with KV Cache Compression}, author = {Adrian Łańcucki and Konrad Staniszewski and Piotr Nawrot and Edoardo M. Ponti}, year = {2025}, eprint = {2506.05345}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.05345v1}, }