Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.
Relative representations of latent spaces enable efficient semantic channel equalization, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Relative Representations with Learned Anchors and Whitened Inner Products
Learned anchors as semantic prototypes combined with whitened inner products improve relative representations, enabling nearly lossless zero-shot communication between heterogeneous neural models on vision and language tasks.