Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs

@inproceedings{zhang2025merge,
  title = {Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs},
  author = {Dingkun Zhang and Shuhan Qi and Xinyu Xiao and Kehai Chen and Xuan Wang},
  year = {2025},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  eprint = {2503.07663},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.07663},
}