CEDAR learns an invertible rotation of vision-language embeddings to concentrate semantics into sparse, axis-aligned coordinates for improved interpretability.
Epic: Explanation of pretrained image classification networks via prototypes
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ProDG generates high-fidelity prototypes from model weights alone for data-free post-hoc explainability in prototype-based networks.
citing papers explorer
-
Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
CEDAR learns an invertible rotation of vision-language embeddings to concentrate semantics into sparse, axis-aligned coordinates for improved interpretability.
-
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
ProDG generates high-fidelity prototypes from model weights alone for data-free post-hoc explainability in prototype-based networks.