@article{batchingawarejointmodelonloadingandofflo, title = {Batching-Aware Joint Model Onloading and Offloading for Hierarchical Multi-Task Inference}, author = {Seohyeon Cha and Kevin Chan and Gustavo de Veciana and Haris Vikalo}, year = {2025}, eprint = {2508.13380}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.13380}, }