English

UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation

Computer Vision and Pattern Recognition 2025-11-24 v1

Abstract

We present UniModel, a unified generative model that jointly supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework. Our goal is to achieve unification along three axes: the model, the tasks, and the representations. At the representation level, we eliminate modality discrepancies by mapping both text and images into a shared visual space: textual prompts are rendered as painted text images on a clean canvas, and all inputs and outputs are treated purely as RGB pixels. This yields a fully vision-native formulation of multimodal learning. At the task level, a broad range of vision-language problems are cast as pixel-to-pixel transformations in this visual space. For understanding tasks, the model takes an RGB image and produces a painted text image that visually encodes the semantic prediction. For generation tasks, painted text images serve as visual conditions that guide realistic and semantically aligned image synthesis. Captioning and text-to-image generation thus become different directions of the same underlying visual translation process. At the model level, we instantiate a single Unified Diffusion Transformer trained with rectified flow in pixel space. A shared backbone jointly learns bidirectional mappings between natural images and painted text images, with lightweight task embeddings to specify the desired direction. Experiments on text-to-image synthesis and image-to-text understanding demonstrate strong cross-modal alignment and emergent controllability such as cycle-consistent image-caption-image loops. Our initial exploration suggests that unifying model, tasks, and representations in a single visual space is a promising paradigm for general-purpose multimodal intelligence.

Keywords

Cite

@article{arxiv.2511.16917,
  title  = {UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation},
  author = {Chi Zhang and Jiepeng Wang and Youming Wang and Yuanzhi Liang and Xiaoyan Yang and Zuoxin Li and Haibin Huang and Xuelong Li},
  journal= {arXiv preprint arXiv:2511.16917},
  year   = {2025}
}
R2 v1 2026-07-01T07:48:15.775Z