arXivJiamin Chen, Qianben Chen, Jiawen Zhang, Yidi Wu, Yuchen Li, Xiaokun Zhang, Wangchunshu Zhou, Chen MaThu, May 28, 2026, 8:35 AM PDT
score 14.7
Diagnostic benchmark reveals hidden flaws in long-form video generation
Original: DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation
Source: arxiv.org ↗
Writing ELI5 summary…