PAWBench: How Far Are We from Probabilistically Aligned World Modeling?

Research official + media 2 src. ~1 min

Formalizes 'probabilistic alignment' as a distributional criterion for video generators acting as stochastic samplers of world dynamics, and ships PAWBench + PAWEval across 50 scenarios and 11 systems. Across all evaluated generators, none consistently matches reference probabilities while preserving the range of valid behaviors.

Why it matters

Top-voted HF Daily Papers entry for Aug 28 at 43 upvotes; shifts the world-model evaluation conversation from per-video plausibility to distribution recovery, exposing a systematic failure mode of current generative video systems.

Importance: 2/5

official+media confirmation; HF Daily 43 upvotes

Sources