SafetyALFRED: Evaluating safety-aware planning of multimodal large language models
[Daily Paper] SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
AI summary
SafetyALFRED 是一个面向多模态大语言模型的评测基准，用于评估其规划过程是否具备安全意识。
[Daily Paper] SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
SafetyALFRED 是一个面向多模态大语言模型的评测基准，用于评估其规划过程是否具备安全意识。