Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models Paper • 2602.24264 • Published 4 days ago • 14
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models Paper • 2602.24264 • Published 4 days ago • 14
Does Data Scaling Lead to Visual Compositional Generalization? Paper • 2507.07102 • Published Jul 9, 2025 • 2
CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally Paper • 2502.03566 • Published Feb 5, 2025 • 4
Diffusion Classifiers Understand Compositionality, but Conditions Apply Paper • 2505.17955 • Published May 23, 2025 • 22