# UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning

arXiv: https://arxiv.org/abs/2508.11196 · HTML: https://mlsanity.com/paper/2508.11196/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 52 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models](https://mlsanity.com/paper/2504.11468/) (2025)
- [RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback](https://mlsanity.com/paper/2402.03681/) (2024)
- [Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2503.13939/) (2025)
- [OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles](https://mlsanity.com/paper/2503.17352/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment](https://mlsanity.com/paper/2312.06960/) (2023)
- [G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning](https://mlsanity.com/paper/2505.13426/) (2025)
- [UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles](https://mlsanity.com/paper/2410.11125/) (2024)
- [HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes](https://mlsanity.com/paper/2409.19833/) (2024)

## Built on by (most cited first, 3 of 3)

- [GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning](https://mlsanity.com/paper/2509.25026/) (2025)
- [GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes](https://mlsanity.com/paper/2511.22645/) (2025)
- [Large Language Model-Assisted UAV Operations and Communications: A Multifaceted Survey and Tutorial](https://mlsanity.com/paper/2602.19534/) (2026)

## Abstract (arXiv)

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.