Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
Diffusion classifiers understand compositionality, but conditions apply.arXiv preprint arXiv:2505.17955, 2
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
citing papers explorer
-
When Do Diffusion Models learn to Generate Multiple Objects?
Using the mosaic controlled dataset framework, experiments show scene complexity dominates over concept imbalance in diffusion model failures for multi-object generation, with counting especially hard in low-data regimes and compositional generalization collapsing under held-out combinations.
-
Video models are zero-shot learners and reasoners
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.