Preprint
Feb 2026
Video-HOCA: A Diagnostic Benchmark for Physical Anomaly Reasoning in Video-LLMs
Video-HOCA, a diagnostic benchmark for physical anomaly reasoning in videos, is introduced and it is found that recognition outpaces explanation: Task I scores cluster at 75-88, while Task II macro-F1 stays mostly below 50.
Chang Liu, Yunfan Ye, Qingyang Zhou et al.
· 0 citations