In recent years, advances in the large-scale pretraining of language and text-to-image models have revolutionized the field of machine learning. Yet, integrating these two modalities into a single, robust model capable of generating seamless multimodal outputs remains a significant challenge. To address this gap, we present the Joint Autoregressive Mixture (JAM) framework, a modular approach that systematically fuses existing text and image generation models. We also introduce a specialized, data-efficient instruction-tuning strategy, tailored for mixed-modal generation tasks. Our final instruct-tuned model demonstrates unparalleled performance in generating high-quality multimodal outputs and represents the first model explicitly designed for this purpose.
@article{arxiv.2309.15564,
title = {Jointly Training Large Autoregressive Multimodal Models},
author = {Emanuele Aiello and Lili Yu and Yixin Nie and Armen Aghajanyan and Barlas Oguz},
journal= {arXiv preprint arXiv:2309.15564},
year = {2023}
}