研究人员推出了一种新颖的多模态框架 Falcon，专为 X 射线行李筛查中的组合威胁推理而设计。与传统的以物体为中心的模型不同，Falcon 侧重于分散组件的功能兼容性来评估风险。该框架将区域特征抽象为结构化的安全状态，从而实现更连贯的威胁评估，并将组合安全推理确立为多模态系统的新评估范式。还开发了一个新的基准 Falcon-X 来评估此能力。 AI
影响 这项研究通过改进多模态模型中的关系推理，可能带来更复杂的安全关键应用 AI 系统。
排序理由 该集群描述了一篇介绍新框架和基准的新研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.25701v1 Announce Type: new Abstract: Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray baggage screening, however, threat often emerges not from a single object but from th…
Conventional vision-language models are largely object-centric, focusing on detecting and describing individual entities. In safety-critical X-ray baggage screening, however, threat often emerges not from a single object but from the functional compatibility of spatially disperse…