Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains 文章

ArXiv CS.CV2026-08-11PAPERen作者: Diandian Zhang, Tingyu Song, Lin Fu, Zheyuan Yang, Yilun Zhao

详细信息

来源站点
ArXiv CS.CV
作者
Diandian Zhang, Tingyu Song, Lin Fu, Zheyuan Yang, Yilun Zhao
文章类型
PAPER
语言
en
发布日期
2026-08-11

摘要

arXiv:2608.09873v1 Announce Type: new Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four core disciplines: Natural Science, Healthcare, Humanities & Social Sciences, and Engineering. Each example requires models to generate temporally rich videos that demand scientific reasoning and knowledge-grounded synthesis, going beyond surface-level visual plausibility. We further establish a rubric-based evaluation protocol. Our analysis shows that, under this protocol, both non-expert human evaluators and MLLM-as-Judge systems can achieve relatively high agreement with expert judgments, supporting reproducible evaluation at scale.