CLIP relies on high-complexity additive binding that prevents generalization to unseen concept combinations, whereas transformers trained from scratch develop low-complexity multiplicative binding functions that enable systematic generalization with sufficient data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How can embedding models bind concepts?
CLIP relies on high-complexity additive binding that prevents generalization to unseen concept combinations, whereas transformers trained from scratch develop low-complexity multiplicative binding functions that enable systematic generalization with sufficient data.