# Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning

arXiv: https://arxiv.org/abs/2509.21976 · HTML: https://mlsanity.com/paper/2509.21976/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 73 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 30 of 51)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning](https://mlsanity.com/paper/2310.09478/) (2023)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Visual-RFT: Visual Reinforcement Fine-Tuning](https://mlsanity.com/paper/2503.01785/) (2025)
- [R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization](https://mlsanity.com/paper/2503.10615/) (2025)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [GRES: Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2306.00968/) (2023)
- [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning](https://mlsanity.com/paper/1805.10002/) (2018)
- [RSGPT: A Remote Sensing Vision Language Model and Benchmark](https://mlsanity.com/paper/2307.15266/) (2023)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)

## Built on by (most cited first, 20 of 20)

- [GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes](https://mlsanity.com/paper/2511.22645/) (2025)
- [SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Images](https://mlsanity.com/paper/2512.20013/) (2025)
- [RemoteAgent: Bridging Vague Human Intents and Earth Observation with RL-based Agentic MLLMs](https://mlsanity.com/paper/2604.07765/) (2026)
- [RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning](https://mlsanity.com/paper/2601.21634/) (2026)
- [GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics](https://mlsanity.com/paper/2602.12617/) (2026)
- [ViLaCD-R1: A Vision-Language Framework for Semantic Change Detection in Remote Sensing](https://mlsanity.com/paper/2512.23244/) (2025)
- [GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision](https://mlsanity.com/paper/2603.09551/) (2026)
- [RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation](https://mlsanity.com/paper/2604.17243/) (2026)
- [WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understanding](https://mlsanity.com/paper/2607.10120/) (2026)
- [A Training-Free Guess What Vision Language Model from Snippets to Open-Vocabulary Object Detection](https://mlsanity.com/paper/2601.11910/) (2026)
- [FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery](https://mlsanity.com/paper/2602.19190/) (2026)
- [UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmark](https://mlsanity.com/paper/2603.10722/) (2026)
- [GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision](https://mlsanity.com/paper/2607.01050/) (2026)
- [HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning](https://mlsanity.com/paper/2607.15255/) (2026)
- [RS-HyRe-R1: A Hybrid Reward Mechanism to Overcome Perceptual Inertia for Remote Sensing Images Understanding](https://mlsanity.com/paper/2604.17504/) (2026)
- [Earth Science Foundation Models: From Perception to Reasoning and Discovery](https://mlsanity.com/paper/2605.12542/) (2026)
- [FUSAR-R1: A Large-Scale Reasoning Model for Intelligent Interpretation of SAR Images](https://mlsanity.com/paper/2607.16819/) (2026)
- [Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?](https://mlsanity.com/paper/2607.20284/) (2026)
- [GeoRefer-Bench: A Benchmark from Referring Pixels to Verifiable Geospatial Reasoning](https://mlsanity.com/paper/2609.29541/) (2026)
- [Knowing Whether, Not Just Where: Anchor-Probing Distillation for Open-Set Remote Sensing Visual Grounding](https://mlsanity.com/paper/2610.13535/) (2026)

## Abstract (arXiv)

Referring expression understanding in remote sensing poses unique challenges, as it requires reasoning over complex object-context relationships. While supervised fine-tuning (SFT) on multimodal large language models achieves strong performance with massive labeled datasets, they struggle in data-scarce scenarios, leading to poor generalization. To address this limitation, we propose Geo-R1, a reasoning-centric reinforcement fine-tuning (RFT) paradigm for few-shot geospatial referring. Geo-R1 enforces the model to first generate explicit, interpretable reasoning chains that decompose referring expressions, and then leverage these rationales to localize target objects. This "reason first, then act" process enables the model to make more effective use of limited annotations, enhances generalization, and provides interpretability. We validate Geo-R1 on three carefully designed few-shot geospatial referring benchmarks, where our model consistently and substantially outperforms SFT baselines. It also demonstrates strong cross-dataset generalization, highlighting its robustness. Code and data will be released at: https://github.com/Geo-R1/geo-r1.