arXivYiqi Liu, Ruifeng Yuan, Yang Wang, Long Li, Fengyu Cai, Hou Pong Chan, Jialin Yu, Hao Zhang, Chenghua Lin, Chenghao XiaoFri, Oct 2, 2026, 10:24 AM PDT
score 15.2
New benchmark tests how well video AI models understand physics
Original: World Embedding Benchmark
Source: arxiv.org ↗
Writing ELI5 summary…