About this paper
A rubric-based diagnostic benchmark and judge assess physical commonsense in text-to-video generation, showing that current models still struggle and that the judge aligns closely with human judgments.
As text-to-video (T2V) models are increasingly positioned as world simulators, it is essential to evaluate whether their videos conform to physical commonsense. However, existing benchmarks rely on annotators who rate each video with a single score based on intuition, yielding ratings that are subjective and do not tell which physical principle is violated. We introduce PhyRubric, a rubric-grounded diagnostic framework for evaluating physical commonsense in T2V generation. For each caption, PhyRubric constructs a caption-specific rubric before any video is seen, decomposing the caption into semantic and physical items, and derives scores from item-level verdicts grounded in timestamped…
text-to-video (T2V) modelsT2V generationworld simulatorsphysical commonsense evaluationrubric-grounded diagnostic frameworkcaption-specific rubricitem-level verdictstimestamped evidencePhyRubric-BenchPhyRubric-Train
- Upvotes
- 4
- Authors
- 8
- Published
- Nov 10, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
PhyRubric: Rubric-Grounded Diagnostic Evaluation of Physical Commonsense in Text-to-Video Generation was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 21 checks on 3 different days. Its best position was #17 of 30, reached on Nov 12, 03:28 UTC. It dropped off the list after Nov 13, 09:28 UTC.