Multi-modal Large Language Models (MLLMs) have demonstrated impressive instruction abilities across various open-ended tasks. However, previous methods primarily focus on enhancing multi-modal capabilities. In this work, we introduce a versatile multi-modal large language model, mPLUG-Owl2, which effectively leverages modality collaboration to improve performance in both text and multi-modal tasks. mPLUG-Owl2 utilizes a modularized network design, with the language decoder acting as a universal interface for managing different modalities. Specifically, mPLUG-Owl2 incorporates shared functional modules to facilitate modality collaboration and introduces a modality-adaptive module that preserves modality-specific features. Extensive experiments reveal that mPLUG-Owl2 is capable of generalizing both text tasks and multi-modal tasks and achieving state-of-the-art performances with a single generic model. Notably, mPLUG-Owl2 is the first MLLM model that demonstrates the modality collaboration phenomenon in both pure-text and multi-modal scenarios, setting a pioneering path in the development of future multi-modal foundation models.
@article{arxiv.2311.04257,
title = {mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration},
author = {Qinghao Ye and Haiyang Xu and Jiabo Ye and Ming Yan and Anwen Hu and Haowei Liu and Qi Qian and Ji Zhang and Fei Huang and Jingren Zhou},
journal= {arXiv preprint arXiv:2311.04257},
year = {2023}
}