# UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning Source: [UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning]() Collection index: [llms.txt]() Data updated: 2026-05-08T05:00:04.262Z Authors: Jiajin Guan, Haibo Mei, Bonan Zhang, Dan Liu, Yuanshuang Fu, Yue Zhang (2) \_\_INSTITUTION\_6\_\_ Research Institute of Electronic Science, Technology, University of Electronic Science, Technology of China, Chengdu, China, (2) School of Aeronautics, Astronautics, University of Electronic Science, Technology of China, Chengdu, China) Published: 2025-08-15T04:06:40.000Z ## Abstract Recent advances in vision-language models (VLMs) have demonstrated strong generalization in natural image tasks. However, their performance often degrades on unmanned aerial vehicle (UAV)-based aerial imagery, which features high resolution, complex spatial semantics, and strict real-time constraints. These challenges limit the applicability of general-purpose VLMs to structured aerial reasoning tasks. To address these challenges, we propose UAV-VL-R1, a lightweight VLM explicitly designed for aerial visual reasoning. It is trained using a hybrid method that combines supervised fine-tuning (SFT) and multi-stage reinforcement learning (RL). We leverage the group relative policy optimization (GRPO) algorithm to promote structured and interpretable reasoning through rule-guided rewards and intra-group policy alignment. To support model training and evaluation, we introduce a high-resolution visual question answering dataset named HRVQA-VL, which consists of 50,019 annotated samples covering eight UAV-relevant reasoning tasks, including object counting, transportation recognition, and spatial scene inference. Experimental results show that UAV-VL-R1 achieves a 48.17% higher zero-shot accuracy than the Qwen2-VL-2B-Instruct baseline and even outperforms its 72B-scale variant, which is 36x larger, on multiple tasks. Ablation studies reveal that while SFT improves semantic alignment, it may reduce reasoning diversity in mathematical tasks. GRPO-based RL compensates for this limitation by enhancing logical flexibility and the robustness of inference. Additionally, UAV-VL-R1 requires only 3.9GB of memory under FP16 inference and can be quantized to 2.5GB with INT8, supporting real-time deployment on resource-constrained UAV platforms. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-task aerial image reasoning on HRVQA-VL (test)](): Multi-task aerial image reasoning; HRVQA-VL (test); Reasoning Accuracy: 72.13. - [Aerial image reasoning on HRVQA-VL 1.0 (test)](): Aerial image reasoning; HRVQA-VL 1.0 (test); Stage A Accuracy: 86.38. ## Original sources and implementation [Original paper]() [PDF]()