{"type":"ScholarlyArticle","title":"Unified Sequence Modeling for Remote Sensing: A Parameter-Efficient Foundation Model via Prompt-Driven Granularity Alignment","authors":[{"name":"Yang Liu","slug":"yang-liu","given":"Yang","family":"Liu","affiliation":""},{"name":"Weixing Luo","slug":"weixing-luo","given":"Weixing","family":"Luo","affiliation":""},{"name":"Huaizhou Qi","slug":"huaizhou-qi","given":"Huaizhou","family":"Qi","affiliation":""},{"name":"Suisui Jia","slug":"suisui-jia","given":"Suisui","family":"Jia","affiliation":""},{"name":"Yongjing Guo","slug":"yongjing-guo","given":"Yongjing","family":"Guo","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/162","url":"https://ijcai.org/proceedings/2026/162","pdf":"https://ijcai.org/proceedings/2026/0162.pdf","markdown":"https://ijcai.org/proceedings/2026/162.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/162","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":162,"pages":{"first":1451,"last":1459},"keywords":["Computer Vision: Machine learning for vision","Machine Learning: Classification","Computer Vision: Recognition (object detection, categorization)"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}