Modality-Specialized Synergizers for Interleaved Vision-Language Generalists
Keywords: vision-language generation, interleaved vision-language instruction tuning
Abstract: Recent advancements in Vision-Language Models (VLMs) have led to the emergence of Vision-Language Generalists (VLGs) capable of understanding and generating both text and images. However, seamlessly generating an arbitrary sequence of text and images remains a challenging task for the current VLGs. One primary limitation lies in applying a unified architecture and the same set of parameters to simultaneously model discrete text tokens and continuous image features. Recent works attempt to tackle this fundamental problem by introducing modality-aware expert models. However, they employ identical architectures to process both text and images, disregarding the intrinsic inductive biases in these two modalities. In this work, we introduce Modality-Specialized Synergizers (MoSS), a novel design that efficiently optimizes existing unified architectures of VLGs with modality-specialized adaptation layers, i.e., a Convolutional LoRA for modeling the local priors of image patches and a Linear LoRA for processing sequential text. This design enables more effective modeling of modality-specific features while maintaining the strong cross-modal integration gained from pretraining. In addition, to improve the instruction-following capability on interleaved text-and-image generation, we introduce LeafInstruct, the first open-sourced interleaved instruction tuning dataset comprising 184,982 high-quality instances on more than 10 diverse domains. Extensive experiments show that VLGs integrated with MoSS achieve state-of-the-art performance, significantly surpassing baseline VLGs in complex interleaved generation tasks. Furthermore, our method exhibits strong generalizability on different VLGs.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 12640
Loading