WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.
VideoPhy: Evaluating physical commonsense for video generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models
WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.