@article{shadownpusystemandalgorithmcodesignfornp,
  title = {ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference},
  author = {Wangsong Yin and Daliang Xu and Mengwei Xu and Gang Huang and Xuanzhe Liu},
  year = {2025},
  eprint = {2508.16703},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.16703},
}