ACL · 2026 · Conference paper · Top venue

Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs

Huanxuan Liao, Shizhu He, Yupu Hao, Yequan Wang, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

Shandong Institute of Automation · Beijing Academy of Artificial Intelligence · Institute of Automation · Fujian Provincial Cancer Hospital · Fuzhou University

Published in
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Date
2026-01-01
Citations
2
Cite
@inproceedings{liao2026spectral,
  title = {Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs},
  author = {Huanxuan Liao and Shizhu He and Yupu Hao and Yequan Wang and Wenhao Teng and Xiangwen Liao and Jun Zhao and Kang Liu},
  year = {2026},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  doi = {10.18653/v1/2026.acl-long.334},
  url = {https://doi.org/10.18653/v1/2026.acl-long.334},
}