SAFIRE is a large-scale benchmark for fire and smoke understanding in multimodal large language models (MLLMs), featuring 83,000 captioned images across 20 scenarios and 193,000 multiple-choice VQA questions derived from a 9.7K-image subset. The benchmark evaluates 10 dimensions of performance, from basic perception to higher-order reasoning, and employs a GPT‑5.4-assisted verification pipeline to ensure annotation quality. Experiments on ten open-source MLLMs (8B–38B) reveal an average accuracy of 61.9%, highlighting significant gaps in safety-critical reasoning, while fine-tuning vision encoders on just 7% of SAFIRE data boosts fire-scene classification accuracy from 20.1% to 64.5%. All resources are publicly available at https://risys-lab.github.io/SAFIRE/.
By Pengfei Li, Naufal Suryanto, Sicheng Zhang, Mohammad Alsharid, Muzammal Naseer
The paper introduces a simulation‑grounded vision‑language model (VLM) framework for wildfire monitoring that converts 2D wildfire simulations into labeled video episodes using a fixed Blender mapping to create low‑detail 3D proxies. These proxies, along with controllable video generation, provide a multimodal memory that a training‑free multi‑agent VLM system uses to retrieve reference episodes, reconcile visual and memory‑based predictions, and generate structured wildfire reports. The system achieves 77.3% accuracy on six simulator‑derived report fields, outperforming direct VLM querying and text‑only memory baselines.
By Duowen Chen, Yuchen Sun, Zhiqi Li, Yuxuan Liao, Sinan Wang, Bart van Bloemen Waanders, Bo Zhu
arXiv:2609.18227v1 Announce Type: new
Abstract: Wildfire smoke detection from satellite imagery is critical for early warning and rapid response. For onboard satellite deployment, detection systems m...
By Sha Lu, Yu Sun, Liang Zhao, Jixue Liu, Lin Liu, Jiuyong Li, A. K. Qin, Alejandro Mousist, Stefan Peters
Wildfire smoke detection from satellite imagery is critical for early warning and rapid response. For onboard satellite deployment, detection systems must operate under strict memory and latency const...
AI4Fire evaluates large language models on wildfire-related tasks, comparing bare (task input only) and grounded (task input plus a task‑specific addition) settings. The study tests six core models on five tasks in zero‑shot mode and expands to 29 additional models, revealing that grounding improves performance when the added information contains the answer, while simple rule‑based approaches often outperform the models. The paper also highlights risks in public releases, such as data leakage that can reveal sensitive information.
By Yue Zhao, Xiyang Hu, Zuobin Xiong, Zhangyu Wang, Ruolin Li
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
The paper introduces ProACT, a performance-driven adaptive training system for virtual reality firefighter training. ProACT adjusts scenario difficulty in real time by linking trainee performance to both global fire spread dynamics and local object flammability. Evaluation demonstrates that ProACT enhances objective training outcomes and user experience compared to existing adaptive and non-adaptive systems.
By Xuan Wang, Jianan Jiang, Rongqian Chen, Tian Lan, Bin Li
arXiv:2609.12078v1 Announce Type: new
Abstract: Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, material state, and visual appearance...
By Aditi Tiwari, Sofia Stoica, Savya Khosla, David Forsyth, Heng Ji
The paper investigates using Vision Language Models (VLMs) to accelerate verification and validation (V&V) of classification models by automatically detecting systematic errors. It introduces a VLM-based error slice detection (ESD) method that groups and labels errors, demonstrating its ability to identify perturbations in a non-military dataset and to cluster images by surroundings in a military context. The study highlights challenges such as underrepresentation of defence data in VLM training and limited contextual diversity, and suggests that while fully automated V&V is not yet feasible, VLMs could speed up the process in the future.
By Dieuwertje Alblas, Alma M. Liezenga, Jan Erik van Woerden, Fedor Taggenbrock, Dalia Aljawaheri, Klamer Schutte
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
arXiv:2603. 29759v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment.
By Qiucheng Yu, Ruijie Xu, Mingang Chen Jianfeng Dong, Xin Tan
arXiv:2603.02465v2 Announce Type: replace-cross
Abstract: Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video dat...
By Emadeldeen Hamdan, Ahmad Faiz Tharima, Mohd Zahirasri Mohd Tohir, Dayang Nur Sakinah Musa, Erdem Koyuncu, Adam J. Watts, Ahmet Enis Cetin