---
title: "Unified Sequence Modeling for Remote Sensing: A Parameter-Efficient Foundation Model via Prompt-Driven Granularity Alignment"
authors:
  - "Yang Liu"
  - "Weixing Luo"
  - "Huaizhou Qi"
  - "Suisui Jia"
  - "Yongjing Guo"
doi: "10.24963/ijcai.2026/162"
url: "https://ijcai.org/proceedings/2026/162"
pdf: "https://ijcai.org/proceedings/2026/0162.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1451-1459"
track: "Main Track"
keywords:
  - "Computer Vision: Machine learning for vision"
  - "Machine Learning: Classification"
  - "Computer Vision: Recognition (object detection, categorization)"
---

# Unified Sequence Modeling for Remote Sensing: A Parameter-Efficient Foundation Model via Prompt-Driven Granularity Alignment

Yang Liu, Weixing Luo, Huaizhou Qi, Suisui Jia, Yongjing Guo

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1451-1459. DOI: [10.24963/ijcai.2026/162](https://doi.org/10.24963/ijcai.2026/162)

## Abstract

Current remote sensing (RS) perception systems suffer from task heterogeneity, necessitating distinct architectures for classification, localization, and reasoning. While vision--language models (VLMs) offer a route toward unification, their computational cost can hinder deployment. In this work, we propose RS-Florence, a compact unified model that addresses these tasks through a Prompt-Driven Sequence-to-Sequence framework. Unlike traditional approaches that segregate semantic understanding and geometric localization, RS-Florence maps images and task-specific prompts into a unified sequence of natural language and discrete geometric tokens. This formulation helps bridge high-level semantics and low-level pixel perception. Experiments across 4 task families and 8 benchmarks show that our 0.23B model remains competitive with task-specific specialists. These results also suggest that multitask joint training improves performance on several benchmarks over single-task fine-tuning, indicating that a shared prompt-driven interface can serve both language and geometry tasks.