PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not only a plausible trajectory, but also the distribution of possible behaviors under the same initial observation and action. We call this distribution-level requirement probabilistic alignment. However, existing evaluations largely assess individual-video plausibility and do not test whether repeated generations recover the correct distribution. This raises a central question: how far are current video generators fro
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- LinkedLinked via arxiv author · 85%Yuandong Pu →
“PAWBench: How Far Are We from Probabilistically Aligned World Modeling?”
- LinkedLinked via arxiv author · 85%Le Zhuo →
“PAWBench: How Far Are We from Probabilistically Aligned World Modeling?”
- LinkedLinked via arxiv author · 85%Sayak Paul →
“PAWBench: How Far Are We from Probabilistically Aligned World Modeling?”
- LinkedLinked via arxiv author · 85%Gabriel Jorge Menezes →
“PAWBench: How Far Are We from Probabilistically Aligned World Modeling?”
- LinkedLinked via arxiv author · 85%Avram Đorđević →
“PAWBench: How Far Are We from Probabilistically Aligned World Modeling?”
- LinkedLinked via arxiv author · 85%Shiyang Li →
“PAWBench: How Far Are We from Probabilistically Aligned World Modeling?”