arXiv AI
Distilling Vision-Language Models for On-Device Fire Understanding
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 10
SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs
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/.
arXiv Computer Vision
1d ago
WISE: A Lightweight, Weakly-Supervised Model for Onboard Fire Smoke Detection and Localization
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...
Hugging Face Trending Papers
2d ago
WISE: A Lightweight, Weakly-Supervised Model for Onboard Fire Smoke Detection and Localization
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...
arXiv Computer Vision
4d ago
Feature Recovery for Object Understanding After Irreversible Fire Damage
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...
arXiv Computer Vision
Sep 11
Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions
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.
arXiv Computer Vision
2d ago
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...