@article{towardrobustandefficientmlbasedgpucachin,
  title = {Toward Robust and Efficient ML-Based GPU Caching for Modern Inference},
  author = {Peng Chen and Jiaji Zhang and Hailiang Zhao and Yirong Zhang and Shenyao Chen and Jiahong Yu and Xueyan Tang and Yixuan Wang and Hao Li and Jianping Zou and Gang Xiong and Kingsum Chow and Shuibing He and Shuiguang Deng},
  year = {2025},
  eprint = {2509.20979},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.20979},
}