The strategic integration of visual, auditory, gestural modalities in current Traditional Chinese Medicine (TCM) popularization short videoson Douyin has markedly enhanced the viewing experience. Yet
该数据集是为论文《VLSBench: Unveiling Information Leakage In Multimodal Safety》创建的，主要用于评估当前多模态大语言模型（MLLMs）的安全能力。数据集包含多个特征，如指令ID、指令、图像路径、类别、子类别和来源。数据集的统计信息和示例图像在README中有所展示。数据集的创建旨在用于研究目的，不涉及用户去匿名化，并已通过机构审查委员会（
# WebClick: A Multimodal Localization Benchmark for Web-Navigation Models We introduce WebClick, a high-quality benchmark dataset for evaluating navigation and localization capabilities of multimoda
