研究人员正在评估AI模型在专业领域的安全性和可靠性。arXiv上的一项研究考察了视觉-语言-动作模型，发现即使在识别到危险时，它们也可能默认执行任务。另一项在Hugging Face上发布的关于颅骨缺损重建形状补全基础模型的审计得出结论，认为当前模型在临床实践中不可靠或不可植入，突显了对此类应用可靠的基础模型进行进一步研究的必要性。 AI
影响 强调了在将AI模型部署到医学重建等敏感应用之前，进行严格安全性和可靠性评估的关键需求。
排序理由 两篇研究论文在不同领域评估了AI模型的安全性和可靠性。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.34837v1 Announce Type: new Abstract: Humans exhibit biological sensitivity to safety-critical stimuli that can trigger defensive action. Across three models and two video benchmarks, we investigate whether similar responses emerge in vision-language-action models by ex…
A patient who has lost part of the skull vault needs an implant that fits the defect exactly, and such implants are still drawn by hand in CAD by specialists, which makes each case slow and expensive. The task can be considered as a shape completion problem, so pretrained complet…