Tests whether skew-symmetric (wedge-product) memory in sequence models is broken everywhere or only for associative recall. Replicates a known failure and shows it does not hold for permutation invariant aggregation.
deep-learning transformers pytorch attention associative-memory sequence-models replication-study skew-symmetric linear-attention empirical-study associative-recall wedge-product
-
Updated
Sep 8, 2026 - TeX