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.
URL https://openaccess.thecvf.com/content_ cvpr_2017/html/Johnson_CLEVR_A_Diagnostic_CVPR_2017_paper.html
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Introduces a benchmark with 34,560 instances for selective QA over conflicting multi-source personal memory and compares fusion methods against LLMs.
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.
-
Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison
Introduces a benchmark with 34,560 instances for selective QA over conflicting multi-source personal memory and compares fusion methods against LLMs.