Home / AI Research / FVScore: Specification-Driven Neuro-Symbolic Video Evaluation
FVAI Research
FVScore: Specification-Driven Neuro-Symbolic Video Evaluation
by google · Do Xuan Long, Long T. Le, Yiwen Song, Min-Yen Kan, Tomas Pfister, Yale Song
We introduce Faithfulness Video Score (FVSCORE), a neuro-symbolic framework for specification-driven video generation evaluation. Existing evaluators rely on holistic MLLM judgments or vision-language metrics, yet aligning their scores with human judgments and tracing them to specific temporal violations remain open challenges. FVSCORE addresses these limitations by compiling each video into explicit propositions capturing prompt requirements and implicit propositions capturing unstated physical, temporal, and cross-modal constraints. It grounds each proposition using specialized perceptual tools and evaluates the resulting confidence traces with soft temporal operators inspired by Linear…
Upvotes4
Comments4
Published16 Nov 2026