arXiv AI October 2, 2026 By Wenping Yin, Fabian Desuer, Ziqi Liu, Naixia Mou, Weijia Li, Pedram Ghamisi, Xiao Xiang Zhu, Hao Li

Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping

Read the original on arXiv AI →

The paper introduces GRDisaster, a multi-task geospatial reasoning framework that leverages vision‑language models to interpret, geolocalize, and assess damage in crowdsourced disaster imagery. It builds on a new benchmark dataset of 26,340 images from PhotoMappers, linking volunteer geographic information, street‑view imagery, and remote sensing data across multiple disaster events from 2018 to 2024. GRDisaster combines deterministic and probabilistic cross‑view geolocalization with multi‑view fusion, and introduces spatial reasoning indicators to validate cross‑view matches and quantify disaster severity using expert‑verified annotations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 29

DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization

arXiv:2607. 24856v1 Announce Type: cross Abstract: Social media imagery (SMI) provides timely and fine-grained ground perspectives that are valuable for situational awareness and emergency response.

By Wenping Yin, Ziqi Liu, Naixia Mou, Weijia Li, Danfeng Hong, Hao Li

llms multimodal benchmarks

arXiv Computer Vision

Sep 23

A Multimodal Large Language Model-Driven Framework for Context-Aware UAV Emergency Landing Site Selection

arXiv:2602.01163v2 Announce Type: replace Abstract: Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, tempora...

By Chunliang Hua, Lei Zhang, Jiayang Sun, Chunlan Zeng, Xiao Hu

llms agents computer-vision multimodal benchmarks

arXiv Computer Vision

Sep 16

DisasterInsight: A Multimodal Benchmark for Function-Aware and Grounded Disaster Assessment

arXiv:2601.18493v2 Announce Type: replace Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-ce...

By Sara Tehrani, Yonghao Xu, Leif Haglund, Amanda Berg, Gulnaz Zhambulova, Michael Felsberg

llms fine-tuning multimodal benchmarks

arXiv Computer Vision

Sep 21

DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response

DisasterInsight is a building‑centric benchmark designed to evaluate vision‑language models (VLMs) for disaster response. Built on the xBD satellite dataset, it adds OpenStreetMap‑derived functional labels to 134,108 building instances and offers 15 task types, including instance assessment, scene counting, multi‑instance reasoning, and structured report generation. Experiments show that VLMs excel at visible damage detection but struggle with building function, multi‑instance reasoning, counting, and grounded reporting, and instruction tuning only partially mitigates these gaps.

By Sara Tehrani, Yonghao Xu, Leif Haglund, Amanda Berg, Gulnaz Zhambulova, Michael Felsberg

llms fine-tuning benchmarks

arXiv Machine Learning

Sep 10

Observing Health Outcomes Using Remote Sensing Imagery and Geo-Context Guided Visual Transformer

The paper introduces the Geo-Context Guided Visual Transformer, a model that augments remote sensing image analysis with geospatial embeddings and an asymmetric attention module. By converting heterogeneous geospatial variables into patch-aligned representations and assigning geospatial roles to attention heads, the approach improves disease prevalence prediction over existing vision-language and graph-based baselines. Ablation and visualization studies demonstrate its effectiveness and interpretability for health-related remote sensing tasks, especially when comprehensive geospatial data are scarce.

By Yu Li, Guilherme N. DeSouza, Praveen Rao, Chi-Ren Shyu

llms rag computer-vision multimodal benchmarks safety

arXiv AI

Jun 16

UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics

arXiv:2606. 15890v1 Announce Type: new Abstract: Understanding urban wellbeing from multimodal data requires integrating heterogeneous spatial and temporal signals, posing significant challenges for current multimodal large language models (MLLMs).

By Yanxin Xi, Xiang Su, Jie Feng, Yu Liu, Sasu Tarkoma, Pan Hui

llms multimodal benchmarks safety

One email a morning, machine-written

Related stories

DisasterTD: Disaster Toponym Disambiguation Using Multimodal LLMs and Cross-View Geolocalization

A Multimodal Large Language Model-Driven Framework for Context-Aware UAV Emergency Landing Site Selection

DisasterInsight: A Multimodal Benchmark for Function-Aware and Grounded Disaster Assessment

DisasterInsight: A Building-Centric Benchmark for Evaluating Vision--Language Models in Disaster Response

Observing Health Outcomes Using Remote Sensing Imagery and Geo-Context Guided Visual Transformer

UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics