Continual Learning with Vision-Language Models via Semantic-Geometry Preservation

@article{he2026continual,
  title = {Continual Learning with Vision-Language Models via Semantic-Geometry Preservation},
  author = {Chi-Yuan He and Zi-Huan Qiu and Fanman Meng and Runtong Zhang and Linfeng Xu and Qingbo Wu and Hongliang Li},
  year = {2026},
  journal = {IEEE transactions on circuits and systems for video technology (Print)},
  eprint = {2603.12055},
  archivePrefix = {arXiv},
  doi = {10.1109/TCSVT.2026.3723096},
  url = {https://arxiv.org/abs/2603.12055},
}