PAWBench: Does a video model capture not only what can happen, but how often?
RisingSayak · x · 2026-08-28
A video model might generate a convincing die roll, yet produce the same few outcomes repeatedly. This paper asks: Does the model capture not only what can happen, but how often? Introducing PAWBench.
Related event: PAWBench Reveals Video Generators Fail Probabilistic Alignment Tests(5 posts)→
More from Research
- ECCV 2026 Paper: Multi-Key Episodic Memory for Video — CSProfKGD · 2026-08-28
- Shunyu Yao: RL finally works, marking the start of AI's 'Second Half' — dejavucoder · 2026-08-28
- Zero-WAM: robots learn unseen tasks from a single human demo video, no fine-tuning — deepakpathak · 2026-08-28
- LeVJEPA: Video Pretraining Without Complex Components — randall_balestr · 2026-08-28
- Study: Task Diversity Inhibits Continual Reinforcement Learning — RubenEVillegas · 2026-08-28
- AI reconstruction reveals plasma jet physics in galaxy — bravo_abad · 2026-08-28