Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
Diffusion classifiers understand compositionality, but conditions apply.arXiv preprint arXiv:2505.17955, 2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Video models are zero-shot learners and reasoners
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.