Information comes in diverse modalities. Multimodal native AI models are essential to integrate real-world information and deliver comprehensive understanding. While proprietary multimodal native models exist, their lack of openness imposes obstacles for adoptions, let alone adaptations. To fill this gap, we introduce Aria, an open multimodal native model with best-in-class performance across a wide range of multimodal, language, and coding tasks. Aria is a mixture-of-expert model with 3.9B and 3.5B activated parameters per visual token and text token, respectively. It outperforms Pixtral-12B and Llama3.2-11B, and is competitive against the best proprietary models on various multimodal tasks. We pre-train Aria from scratch following a 4-stage pipeline, which progressively equips the model with strong capabilities in language understanding, multimodal understanding, long context window, and instruction following. We open-source the model weights along with a codebase that facilitates easy adoptions and adaptations of Aria in real-world applications.
@article{arxiv.2410.05993,
title = {Aria: An Open Multimodal Native Mixture-of-Experts Model},
author = {Dongxu Li and Yudong Liu and Haoning Wu and Yue Wang and Zhiqi Shen and Bowen Qu and Xinyao Niu and Fan Zhou and Chengen Huang and Yanpeng Li and Chongyan Zhu and Xiaoyi Ren and Chao Li and Yifan Ye and Peng Liu and Lihuan Zhang and Hanshu Yan and Guoyin Wang and Bei Chen and Junnan Li},
journal= {arXiv preprint arXiv:2410.05993},
year = {2025}
}