Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models Paper โข 2602.24264 โข Published 14 days ago โข 14
CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally Paper โข 2502.03566 โข Published Feb 5, 2025 โข 4
Fast and Simple Explainability for Point Cloud Networks Paper โข 2403.07706 โข Published Mar 12, 2024
Whitened CLIP as a Likelihood Surrogate of Images and Captions Paper โข 2505.06934 โข Published May 11, 2025
EPiC: Ensemble of Partial Point Clouds for Robust Classification Paper โข 2303.11419 โข Published Mar 20, 2023 โข 1
EPiC: Ensemble of Partial Point Clouds for Robust Classification Paper โข 2303.11419 โข Published Mar 20, 2023 โข 1