@inproceedings{yu-etal-2025-progressive,
    title = "Progressive {L}o{RA} for Multimodal Continual Instruction Tuning",
    author = "Yu, Yahan  and
      Zhang, Duzhen  and
      Ren, Yong  and
      Zhao, Xuanle  and
      Chen, Xiuyi  and
      Chu, Chenhui",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.143/",
    pages = "2779--2796",
    ISBN = "979-8-89176-256-5",
    abstract = "Multimodal Continual Instruction Tuning (MCIT) empowers Multimodal Large Language Models (MLLMs) to adapt to ever-evolving requirements without continuous costly retraining. However, MCIT faces challenges in mitigating Catastrophic Forgetting (CF) and enhancing Knowledge Transfer (KT). Existing works combine Mixture-of-Expert (MoE) and LoRA to address these. However, using a fixed number of shared LoRA blocks across tasks can lead to the overwriting of acquired knowledge, making MLLMs harder to handle CF and KT. Therefore, we propose the **Prog**ressive **LoRA** framework (ProgLoRA), which contains a progressive LoRA pool and trains a new LoRA block for each incremental task to reduce knowledge interference. Specifically, ProgLoRA has two key mechanisms: task-aware allocation for effectively leveraging acquired knowledge at current task and task recall for realigning the model with learned tasks. Additionally, considering different application scenarios, we design a static ProgLoRA for the more idealized basic setting and a dynamic ProgLoRA for the more realistic challenging setting. Experiments on the latest MCIT benchmark demonstrate that ProgLoRA outperforms existing approaches."
}