@article{hybridserveefficientservingoflargeai,
  title = {HybridServe: Efficient Serving of Large AI Models with Confidence-Based Cascade Routing},
  author = {Leyang Xue and Yao Fu and Luo Mai and Mahesh K. Marina},
  year = {2025},
  eprint = {2505.12566},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.12566v1},
}