Jointly Training Large Autoregressive Multimodal Models

Aiello Emanuele, Yu Lili, Nie Yixin, Aghajanyan Armen, Oguz Barlas. Arxiv 2023

[Paper]    
Fine Tuning GPT Multimodal Models Pretraining Methods Tools Training Techniques

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.

Similar Work