@article{whencompressionmeetsmodelcompression,
  title = {When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models},
  author = {Weilan Wang and Yu Mao and Dongdong Tang and Hongchao Du and Nan Guan and Chun Jason Xue},
  year = {2025},
  eprint = {2502.15443},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.15443v1},
}