Introduction
Recent advancements in unified multimodal understanding and visual generation (or multimodal generation) models have been hindered by their quadratic computational complexity and dependence on large-scale training data. We present OmniMamba, the first linear-architecture-based multimodal generation model that generates both text and images through a unified next-token prediction paradigm. The model fully leverages Mamba-2's high computational and memory efficiency, extending its capabilities from text generation to multimodal generation. To address the data inefficiency of existing unified models, we propose two key innovations: (1) decoupled vocabularies to guide modality-specific generation, and (2) task-specific LoRA for parameter-efficient adaptation. Furthermore, we introduce a decoupled two-stage training strategy to mitigate data imbalance between two tasks. Equipped with these techniques, OmniMamba achieves competitive performance with JanusFlow while surpassing Show-o across benchmarks, despite being trained on merely 2M image-text pairs, which is 1,000 times fewer than Show-o. Notably, OmniMamba stands out with outstanding inference efficiency, achieving up to a 119.2X speedup and 63% GPU memory reduction for long-sequence generation compared to Transformer-based counterparts.
Paper: https://arxiv.org/abs/2503.08686
Code: https://github.com/hustvl/OmniMamba
Citation
If you find OmniMamba useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.
@misc{zou2025omnimambaefficientunifiedmultimodal,
title={OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models},
author={Jialv Zou and Bencheng Liao and Qian Zhang and Wenyu Liu and Xinggang Wang},
year={2025},
eprint={2503.08686},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.08686},
}