English

Jointly Training Large Autoregressive Multimodal Models

Machine Learning 2023-09-29 v2 Computation and Language Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-28T12:33:37.268Z