← back
arXivOscar Chew, Serhii Honcharenko, Qian-Hui Chen, Patricia Lu, Dishant Zaveri, Khoa D. Doan, Kuan-Hao HuangTue, May 26, 2026, 7:41 AM PDT
score 16.4

Video AI models confuse events across unrelated clips

Original: Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models

Source: arxiv.org

Writing ELI5 summary…