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
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Introduces a benchmark with 34,560 instances for selective QA over conflicting multi-source personal memory and compares fusion methods against LLMs.
ASPEn integrates ASP stable-model semantics with energy-based models for joint discrete-continuous optimisation and end-to-end training on visual reasoning and multi-object tracking.
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.
-
Answer Set Programming Energised! End-to-End Neurosymbolic Reasoning and Learning with ASP and Energy Based Models
ASPEn integrates ASP stable-model semantics with energy-based models for joint discrete-continuous optimisation and end-to-end training on visual reasoning and multi-object tracking.