@article{probeandskipselfpredictivetokenskippingf,
  title = {Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference},
  author = {Zimeng Wu and Donghao Wang and Chaozhe Jin and Jiaxin Chen and Yunhong Wang},
  year = {2026},
  eprint = {2601.13155},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.13155},
}