@article{patel2026tokengate,
    title={{TokenGate}: Adapting {LLMs} for Fast and Memory-Efficient Prefill with Learned Token Pruning},
    author={Liana Patel and Rishabh Ranjan and Ion Stoica and Matei Zaharia and Carlos Guestrin},
    journal={arXiv preprint arXiv:2610.26754},
    year={2026}
}