Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.23219 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915697971429376 |
|---|---|
| author | Dai, Shiqi Ma, Zizhi Luo, Zhicong Yang, Xuesong Huang, Yibin Zhang, Wanyue Chen, Chi Guo, Zonghao Xu, Wang Sun, Yufei Sun, Maosong |
| author_facet | Dai, Shiqi Ma, Zizhi Luo, Zhicong Yang, Xuesong Huang, Yibin Zhang, Wanyue Chen, Chi Guo, Zonghao Xu, Wang Sun, Yufei Sun, Maosong |
| contents | While Multimodal Large Language Models (MLLMs) have exhibited remarkable general intelligence across diverse domains, their potential in low-altitude applications dominated by Unmanned Aerial Vehicles (UAVs) remains largely underexplored. Existing MLLM benchmarks rarely cover the unique challenges of low-altitude scenarios, while UAV-related evaluations mainly focus on specific tasks such as localization or navigation, without a unified evaluation of MLLMs'general intelligence. To bridge this gap, we present MM-UAVBench, a comprehensive benchmark that systematically evaluates MLLMs across three core capability dimensions-perception, cognition, and planning-in low-altitude UAV scenarios. MM-UAVBench comprises 19 sub-tasks with over 5.7K manually annotated questions, all derived from real-world UAV data collected from public datasets. Extensive experiments on 16 open-source and proprietary MLLMs reveal that current models struggle to adapt to the complex visual and cognitive demands of low-altitude scenarios. Our analyses further uncover critical bottlenecks such as spatial bias and multi-view understanding that hinder the effective deployment of MLLMs in UAV scenarios. We hope MM-UAVBench will foster future research on robust and reliable MLLMs for real-world UAV intelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios? Dai, Shiqi Ma, Zizhi Luo, Zhicong Yang, Xuesong Huang, Yibin Zhang, Wanyue Chen, Chi Guo, Zonghao Xu, Wang Sun, Yufei Sun, Maosong Computer Vision and Pattern Recognition While Multimodal Large Language Models (MLLMs) have exhibited remarkable general intelligence across diverse domains, their potential in low-altitude applications dominated by Unmanned Aerial Vehicles (UAVs) remains largely underexplored. Existing MLLM benchmarks rarely cover the unique challenges of low-altitude scenarios, while UAV-related evaluations mainly focus on specific tasks such as localization or navigation, without a unified evaluation of MLLMs'general intelligence. To bridge this gap, we present MM-UAVBench, a comprehensive benchmark that systematically evaluates MLLMs across three core capability dimensions-perception, cognition, and planning-in low-altitude UAV scenarios. MM-UAVBench comprises 19 sub-tasks with over 5.7K manually annotated questions, all derived from real-world UAV data collected from public datasets. Extensive experiments on 16 open-source and proprietary MLLMs reveal that current models struggle to adapt to the complex visual and cognitive demands of low-altitude scenarios. Our analyses further uncover critical bottlenecks such as spatial bias and multi-view understanding that hinder the effective deployment of MLLMs in UAV scenarios. We hope MM-UAVBench will foster future research on robust and reliable MLLMs for real-world UAV intelligence. |
| title | MM-UAVBench: How Well Do Multimodal Large Language Models See, Think, and Plan in Low-Altitude UAV Scenarios? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.23219 |