2 papers
cs.CL2026
Compositional Generalization via Structural Identification in a Category-Theoretic Framework
Akihiro Maeda, Thomas Seiller, Yohei Oseki
Compositional generalization is usually evaluated through model accuracy. We instead ask which structural or lexical identifications make held-out COGS examples admissible from the…
stat.ML2026
Algebraic Signatures for Structural Learning in Probability Tensors
Akihiro Maeda, Shohei Hidaka, Satoshi Aoki
Algebraic statistics characterizes statistical models through polynomial constraints, but it has mainly been used for analytically specified model classes. This paper studies the i…