让下一篇重要论文，不再错过。

原文摘要

We introduce DisasterVL, a dataset and benchmark for evidence-grounded reasoning about disaster imagery. It contains approximately 1.2 million images from 142 countries, paired with 25 million structured annotations covering scene captions, incident and location assessments, spatial relationships, and visual question answering (VQA). The VQA annotations link answers to visible evidence and include questions about both present and absent cues, multiple answer formats, and difficulty labels. Region-level annotations link caption phrases to bounding boxes and spatial relationships to the regions they connect. The test set contains 38,254 images spanning 75 countries and 28 hazard types. Gemini 3.1 Pro audited the test annotations, and human reviewers validated a stratified subset. On this benchmark, the 9B DisasterVLM model outperforms the evaluated general-purpose baselines on captioning, open-ended VQA, incident reasoning, and region-level grounding. Gains in text overlap are larger than gains in evidence scores. We plan to publicly release the dataset, trained models, and code.