@article{indexmemlearnedkvcacheevictionwithlatent,
  title = {IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference},
  author = {Xintong Yang and Hao Gu and Binxing Xu and Lujun Li and Bei Liu and Jiacheng Liu and Qiyuan Zhu and Yike Guo and Sirui Han},
  year = {2026},
  eprint = {2605.25475},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.25475},
}