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

• URL: http://arxiv.org/abs/2511.16917v1
• Date: Fri, 21 Nov 2025 03:02:10 GMT
• Title: UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation
• Authors: Chi Zhang, Jiepeng Wang, Youming Wang, Yuanzhi Liang, Xiaoyan Yang, Zuoxin Li, Haibin Huang, Xuelong Li,
• Abstract summary: We present a unified generative model that supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework.<n>Our goal is to achieve unification along three axes: the model, the tasks, and the representations.<n> Experiments on text-to-image synthesis and image-to-text understanding demonstrate strong cross-modal alignment.
• Score: 51.31795451147935
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• PixelWorld: How Far Are We from Perceiving Everything as Pixels? [62.068243387551085]
  Recent agentic language models increasingly need to interact with real-world environments that contain tightly intertwined visual and textual information.<n>We introduce Perceive Everything as Pixels (PEAP), a benchmark that renders natural-language, tabular, mathematical, and diagrammatic inputs into a shared pixel space.<n>Experiments show that PEAP achieves comparable performance to token-based approaches on semantic understanding tasks.
  arXiv  Detail & Related papers  (2025-01-31T17:39:21Z)
• Linguistic Query-Guided Mask Generation for Referring Image Segmentation [10.130530501400079]
  Referring image segmentation aims to segment the image region of interest according to the given language expression. We propose an end-to-end framework built on transformer to perform Linguistic query-Guided mask generation.
  arXiv  Detail & Related papers  (2023-01-16T13:38:22Z)
• Universal Multimodal Representation for Language Understanding [110.98786673598015]
  This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of images either from a light topic-image lookup table extracted over the existing sentence-image pairs. Then, the text and images are encoded by a Transformer encoder and convolutional neural network, respectively.
  arXiv  Detail & Related papers  (2023-01-09T13:54:11Z)
• Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation [10.39028769374367]
  We present a new framework that takes text-to-image synthesis to the realm of image-to-image translation. Our method harnesses the power of a pre-trained text-to-image diffusion model to generate a new image that complies with the target text.
  arXiv  Detail & Related papers  (2022-11-22T20:39:18Z)
• UNIMO-2: End-to-End Unified Vision-Language Grounded Learning [46.914284894632]
  We propose an end-to-end unified-modal pre-training framework, namely UNIMO-2. We build a unified Transformer model to jointly learn visual representations, textual representations and semantic alignment between images and texts. Our code and models are public at the UNIMO project page.
  arXiv  Detail & Related papers  (2022-03-17T03:53:11Z)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)
• L-Verse: Bidirectional Generation Between Image and Text [41.133824156046394]
  L-Verse is a novel architecture consisting of feature-augmented variational autoencoder (AugVAE) and bidirectional auto-regressive transformer (BiART) Our AugVAE shows the state-of-the-art reconstruction performance on ImageNet1K validation set, along with the robustness to unseen images in the wild. L-Verse can be directly used for image-to-text or text-to-image generation tasks without any finetuning or extra object detection frameworks.
  arXiv  Detail & Related papers  (2021-11-22T11:48:26Z)
• UFO: A UniFied TransfOrmer for Vision-Language Representation Learning [54.82482779792115]
  We propose a single UniFied transfOrmer (UFO) capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concatenation of the image and the question) for vision-language (VL) representation learning. Existing approaches typically design an individual network for each modality and/or a specific fusion network for multimodal tasks.
  arXiv  Detail & Related papers  (2021-11-19T03:23:10Z)
• Text as Neural Operator: Image Manipulation by Text Instruction [68.53181621741632]
  In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We show that the proposed model performs favorably against recent strong baselines on three public datasets.
  arXiv  Detail & Related papers  (2020-08-11T07:07:10Z)
• Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers [46.275416873403614]
  We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding. Our approach makes the most state-of-the-arts in downstream tasks, including Visual Question Answering (VQA), image-text retrieval, Natural Language for Visual Reasoning for Real (NLVR)
  arXiv  Detail & Related papers  (2020-04-02T07:39:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.