Location embeddings from geographic INRs can be decomposed into sparse latent concepts, natural language concepts, and visual features while retaining high reconstruction capability.
Stewart, Caleb Robinson, Isaac A
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Repurposing discarded supervised classification heads from vision models as semantic prototypes boosts post-hoc vision-language alignment methods on retrieval and zero/few-shot classification.
citing papers explorer
-
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
Repurposing discarded supervised classification heads from vision models as semantic prototypes boosts post-hoc vision-language alignment methods on retrieval and zero/few-shot classification.