Recent Multimodal Large Language Models (MLLMs) excel in vision-language understanding but face challenges in adapting to dynamic real-world scenarios that require continuous integration of new knowledge and skills. While continual learning (CL) offers a potential solution, existing benchmarks and methods suffer from critical limitations. In this paper, we introduce MLLM-CL, a novel benchmark encompassing domain and ability continual learning, where the former focuses on independently and identically distributed (IID) evaluation across evolving mainstream domains, whereas the latter evaluates on non-IID scenarios with new model abilities. Methodologically, we propose preventing catastrophic interference through parameter isolation and an MLLM-based routing mechanism. Extensive experiments demonstrate that our approach can integrate domain-specific knowledge and functional abilities with minimal forgetting, significantly outperforming existing methods. Our benchmark and code are available at https://github.com/bjzhb666/MLLM-CL.
@article{arxiv.2506.05453,
title = {MLLM-CL: Continual Learning for Multimodal Large Language Models},
author = {Hongbo Zhao and Fei Zhu and Haiyang Guo and Meng Wang and Rundong Wang and Gaofeng Meng and Zhaoxiang Zhang},
journal= {arXiv preprint arXiv:2506.05453},
year = {2025}
}