Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
Peekaboo: Text to image diffusion models are zero-shot segmentors
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.