The results show that moving from vector-valued to functional parameterizations, with concept and domain sparsity, extends SAEs from representing concept presence to modeling structured concept expression, highlighting the importance of parameterization.
Characterizing the properties of neuronal cell types is central to understanding brain function. Yet, biophysically realistic neuron models remain difficult to scale to large populations while preserving the richness of cellular dynamics and within-cell-type variability. We present a cell-type-specific neural-operator...
Luca Ghafourpour, Cindy Zhao, Valentin Duruisseaux et al.· 0 citations
EquiReg formalizes manifold-preferential equivariant functions that exhibit low equivariance error for on-manifold samples and high error for off-manifold ones, thereby guiding sampling toward symmetry-preserving regions of the solution space.