---
title: "Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing"
authors:
  - "Weiyu Zhang"
  - "Yuan Hu"
  - "Yong Li"
  - "Yu Liu"
doi: "10.24963/ijcai.2026/231"
url: "https://ijcai.org/proceedings/2026/231"
pdf: "https://ijcai.org/proceedings/2026/0231.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "2073-2081"
track: "Main Track"
keywords:
  - "Computer Vision: Vision, language and reasoning"
  - "Natural Language Processing: Language models"
  - "Computer Vision: Image and video synthesis and generation"
---

# Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing

Weiyu Zhang, Yuan Hu, Yong Li, Yu Liu

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 2073-2081. DOI: [10.24963/ijcai.2026/231](https://doi.org/10.24963/ijcai.2026/231)

## Abstract

Unified remote sensing multimodal models exhibit a pronounced spatial reversal curse: although they can accurately recognize and describe object locations in images, they often fail to faithfully execute the same spatial relations during text-to-image generation, where such relations constitute core semantic information in remote sensing. Motivated by this observation, we propose Uni-RS, the first unified multimodal model tailored for remote sensing, to explicitly address the spatial asymmetry between understanding and generation. Specifically, we first introduce explicit Spatial-Layout Planning to transform textual instructions into spatial layout plans, decoupling geometric planning from visual synthesis. We then impose Spatial-Aware Query Supervision to bias learnable queries toward spatial relations explicitly specified in the instruction. Finally, we develop Image–Caption Spatial Layout Variation to expose the model to systematic geometry-consistent spatial transformations. Extensive experiments across multiple benchmarks show that our approach substantially improves spatial faithfulness in text-to-image generation, while maintaining strong performance on multimodal understanding tasks like image captioning, visual grounding, and VQA tasks.