HodgeCover isolates the harmonic kernel of a simplicial Laplacian on an expert 2-complex to identify irreducible merge cycles and selects experts for aggressive compression, matching or exceeding baselines on open-weight MoE models.
Simplicial neural net- works
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
ModernSASST is the first simplicial complex-based spatiotemporal model that combines random walks on high-dimensional complexes with parallelizable temporal convolutional networks for efficient high-order topology capture.
Tutorial on TSP foundations via the combinatorial Hodge Laplacian with an illustrative application to edge signals in brain imaging data.
citing papers explorer
-
HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts
HodgeCover isolates the harmonic kernel of a simplicial Laplacian on an expert 2-complex to identify irreducible merge cycles and selects experts for aggressive compression, matching or exceeding baselines on open-weight MoE models.
-
Modern Structure-Aware Simplicial Spatiotemporal Neural Network
ModernSASST is the first simplicial complex-based spatiotemporal model that combines random walks on high-dimensional complexes with parallelizable temporal convolutional networks for efficient high-order topology capture.
-
Topological Signal Processing: An Application-Oriented Tutorial
Tutorial on TSP foundations via the combinatorial Hodge Laplacian with an illustrative application to edge signals in brain imaging data.
- Topology-Preserving Neural Operator Learning via Hodge Decomposition