WoW-world-model/WoW-1-Benchmark-Samples
收藏Hugging Face2025-10-17 更新2025-10-25 收录
下载链接:
https://hf-mirror.com/datasets/WoW-world-model/WoW-1-Benchmark-Samples
下载链接
链接失效反馈官方服务:
资源简介:
WoW-1基准样本数据集是作为WoW(World-Omniscient World Model)项目的一部分发布的官方评估数据集。这个基准旨在评估用于机器人技术和具身人工智能的生成世界模型在物理一致性和因果推理能力。数据集包含612个表示现实世界机器人交互任务的自然语言提示。
WoW-1 Benchmark Samples is the official evaluation dataset released as part of the WoW (World-Omniscient World Model) project. This benchmark is designed to assess the physical consistency and causal reasoning capabilities of generative world models for robotics and embodied AI. The dataset contains 612 natural language prompts representing real-world robot interaction tasks.
提供机构:
WoW-world-model



