MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer

arXiv:2401.10208v2 Announce Type: replace-cross
Abstract: Developing generative models for interleaved image-text data has both research and practical value. It requires models to understand the interleaved sequences and subsequently generate images and text. However, existing attempts are limited by the issue that the fixed number of visual tokens cannot efficiently capture image details, which is particularly problematic in the multi-image scenarios. To address this, this paper presents MM-Interleaved, an end-to-end generative model for interleaved image-text data. It introduces a multi-scale and …

arxiv cs.cl cs.cv feature generative generative modeling image modal modeling multi-modal text type via