cs.CVNov 10, 2026

UniWeaver: Harnessing Unified Multimodal Models for Interleaved Text-Image Generation

Authors: Hongxu Chen, Zixuan Zhong, Donghao Zhou, Haodong Li, Xiaomin Yu, Tianhao Li, Shiyao Yu, Zhongwei Wan, 

Organizations: OSU · UCL · CUHK · HKUST(GZ) · 

Abstract

Unified multimodal models (UMMs) have opened up new possibilities for generating rich interleaved text-image content. However, they generally lack native support for coordinating the two modalities, and translating coarse user requests into coherent multimodal compositions also requires explicit planning. We propose UniWeaver, a structured, model-agnostic harness framework that integrates multimodal planning, generation, and visual feedback to produce coherent interleaved outputs. To train UMMs for this task, we construct UniWeaver-10K, a dataset of 10,000 tasks across 20 task families, paired with execution trajectories guided by UniWeaver. We also introduce UniWeaver-Bench, a task-oriented benchmark systematically assessing text coverage, writing quality, visual coverage, and image-text alignment. Experiments show that UniWeaver achieves state-of-the-art performance and improves interleaved text-image generation across multiple UMM backbones.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training

    Mar 26, 2026Jinbo Xing, Zeyinzi Jiang, Yuxiang Tuo +15Multimodal GenerationMultimodal Foundation Models

  2. Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

    Jun 29, 2026Chonghuinan Wang, Zhikai Chen, Chunwei Wang +9Unified Multimodal ModelsMultimodal Model Evaluation

  3. IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation

    Oct 28, 2026Shaohan Yu, Jie Qin, Wende Tan +4Multimodal GenerationMultimodal Dataset