# Metadata Source URL:: https://arxiv.org/abs/2112.05253 Topics:: #ai --- # MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning Large-scale pretraining is fast becoming the norm in Vision-Language (VL) modeling. However, prevailing VL approaches are limited by the requirement for labeled data and the use of complex multi-step pretraining objectives. We present MAGMA - a simple method for augmenting generative language models with additional modalities using adapter-based finetuning. Building on Frozen, we train a series of VL models that autoregressively generate text from arbitrary combinations of visual and textual input. The pretraining is entirely end-to-end using a single language modeling objective, simplifying optimization compared to previous approaches. Importantly, the language model weights remain unchanged during training, allowing for transfer of encyclopedic knowledge and in-context learning abilities from language pretraining. MAGMA outperforms Frozen on open-ended generative tasks, achieving state of the art results on the OKVQA benchmark and competitive results on a range of other popular VL benchmarks, while pretraining on 0.2% of the number of samples used to train SimVLM. ## Highlights > [!quote]+ Updated on 161022_112629 > > MAGMA - a simple method for augmenting generative language models with >additional modalities using adapter-based finetuning. Building on Frozen, we >train a series of VL models that autoregressively generate text from arbitrary >combinations of visual and textual input. The pretraining is entirely >end-to-end using a single language modeling objective, simplifying optimization >compared to previous approaches. Importantly, the language model weights remain >unchanged during training, allowing for transfer of encyclopedic knowledge and >in-context learning abilities from language pretraining. MAGMA outperforms >Frozen on open-ended generative tasks, achieving state of the art results on >the OKVQA benchmark and competitive results on a range of other popular VL >benchmarks, while pretraining on 0.2% of the number of samples used to train >SimVLM.