A new 1,000-video benchmark, PhysiXFails, with a 17-category taxonomy of physics failures, shows prompt-tuned large multimodal models outperform video anomaly detectors at detecting and naming physics rule violations in game software.
Guest editorial: Physics-based simulation games,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Runtime Failure Hunting for Physics Engine Based Software Systems: How Far Can We Go?
A new 1,000-video benchmark, PhysiXFails, with a 17-category taxonomy of physics failures, shows prompt-tuned large multimodal models outperform video anomaly detectors at detecting and naming physics rule violations in game software.