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.
arXiv preprint arXiv:2107.08221 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.
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.
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
-
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
Introduces 9 synthetic annotation tasks and benchmarks for behavioral cloning, finding hierarchical skill learning, scaling benefits, effective multi-task pretraining, and shared internal representations of task phases and mistakes.