CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models

@inproceedings{li2025cmt,
  title = {CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models},
  author = {Dongfang Li and Zetian Sun and Xinshuo Hu and Baotian Hu and Min Zhang},
  year = {2025},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  eprint = {2412.07393},
  archivePrefix = {arXiv},
  doi = {10.1609/aaai.v39i23.34619},
  url = {https://arxiv.org/abs/2412.07393},
}