OpenMOSS-Team/FutureOmni
收藏Hugging Face2026-01-22 更新2026-02-07 收录
下载链接：
https://hf-mirror.com/datasets/OpenMOSS-Team/FutureOmni
下载链接
链接失效反馈官方服务：
资源简介：
FutureOmni是第一个旨在评估从音频-视觉环境进行全模态未来预测的基准测试。为了成功，模型必须进行跨模态的因果和时间推理，同时有效利用内部知识来预测未来事件。数据集包含1,034个高质量的多选题QA对，覆盖919个视频。
FutureOmni is the first benchmark designed to evaluate full-modal future prediction from audio-visual environments. To succeed, models must perform cross-modal causal and temporal reasoning while effectively leveraging internal knowledge to predict future events. The dataset comprises 1,034 high-quality multiple-choice QA pairs spanning 919 videos.
提供机构：
OpenMOSS-Team
