SOURCE-LINKED INTELLIGENCE

TPR-Attention for Combinatorial Generalization

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Systematic generalization remains a significant challenge in deep learning. In particular, combinatorial generalization - generalizing to new configurations of known factors of variation - is effortless for humans but difficult for standard neural architectures that rely on statistical correlations rather than explicit structural representations. We introduce a new architectural component that embeds structured inductive bias into deep learning: an attention mechanism operating over tensor-product representations (TPRs). Through controlled experiments on compositional tasks, we show that this

Read original source ↗ Open in workspace

recordType

paper

region

Global