Continual learning enables AI systems to acquire new knowledge while retaining previously learned information. While traditional unimodal methods have made progress, the rise of Multimodal Large Language Models (MLLMs) brings new challenges in Multimodal Continual Learning (MCL), where models are expected to address both catastrophic forgetting and cross-modal coordination. To advance research in this area, we present MCITlib, a comprehensive library for Multimodal Continual Instruction Tuning. MCITlib currently implements 8 representative algorithms and conducts evaluations on 3 benchmarks under 2 backbone models. The library will be continuously updated to support future developments in MCL. The codebase is released at https://github.com/Ghy0501/MCITlib.
@article{arxiv.2508.07307,
title = {MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark},
author = {Haiyang Guo and Fei Zhu and Hongbo Zhao and Fanhu Zeng and Wenzhuo Liu and Shijie Ma and Da-Han Wang and Xu-Yao Zhang},
journal= {arXiv preprint arXiv:2508.07307},
year = {2026}
}