Tag
This controlled study compares geometric algebra (Cl(3,0)) layers against a minimal scalarization baseline for SO(3)-equivariant vector learning, finding that geometric algebra adds no benefit for single-stage tasks but significantly beats scalarization in low-data regimes for deeply composed group operations.
This paper investigates the role of group-equivariant architectures in neural fluid dynamics surrogates, introducing the AB-GATr model. It finds that equivariance is beneficial when data lacks strong alignment, but can degrade performance on highly aligned datasets.