Multilingual multimodal pre-training has garnered significant atten tion, but it faces challenges due to the substantial need for diverse CCSCONCEPTS • Computing methodologies Machine learning; Machine learning approaches; Neural networks; Artificial intelligence; Com multilingual text-image data, especially for minor languages. This article introduces UniGen, a unified strategy for efficient multilin gual multimodal pre-training inspired by internet data distribution observations. Leveraging the richer availability and higher qual ity of multilingual text-English text and English text-image data, UniGen aligns the latent space of multilingual text with visual information to a unified semantic space. This alignment, with English as a reference, proves effective in enhancing cross-modal understanding. UniGen reduces reliance on multilingual text-image data, surpassing comparable models in multilingual multimodal benchmarkIGLUEbyanotable7%. Notably, UniGenisthefirstmul tilingual multimodal model to unify all pre-training tasks within a generative pre-training framework.