Alternatives to UCD4IDS/MultiscaleSimplexSignalTransforms.jl

UCD4IDS/MultiscaleSimplexSignalTransforms.jl: Signal processing on simplicial complexes, using basis dictionaries formed via hierarchical partitioning No license declared. Below, the open repos Take My Repo keeps on the same subjects, most starred first. Stars measure popularity, not quality.

AI on my own machineRepo

SpectRAG

Spectral graph-augmented retrieval for RAG. Augments dense vector search with a weighted chunk graph and its Laplacian spectrum, graph expansion, spectral diffusion, and cluster-aware selection, to retrieve context that is jointly relevant, non-redundant, and connected for multi-hop reasoning.

  • 51
  • Python
  • MIT
  • 3 wk ago
SightAndCiteTake it

Side by side

NameStarsLicenseLanguageLast changeIn commonCompare
UCD4IDS/MultiscaleSimplexSignalTransforms.jl1None declaredJulia2 y ago
shobrook/communities761MITPython3 y agospectral-clusteringCompare
UCD4IDS/MultiscaleGraphSignalTransforms.jl12None declaredJulia8 mo agospectral-clustering, ghwt, graph-laplacianCompare
ruvnet/sublinear-time-solver102MITRust11 d agograph-laplacianCompare
FilippoMB/Spectral-Clustering-with-Graph-Neural-Networks-for-Graph-Pooling278MITPython21 mo agospectral-clusteringCompare
SightAndCite/SpectRAG51MITPython3 wk agograph-laplacianCompare
Dref360/spectral-metric46MITPython3 y agospectral-clusteringCompare
FilippoMB/Simplifying-Clustering-with-Graph-Neural-Networks38MITPython19 mo agospectral-clusteringCompare
ahb-sjsu/the-angular-observer4MITTeX8 wk agospectral-clustering, graph-laplacianCompare
FilippoMB/Total-variation-graph-neural-networks20MITPython21 mo agospectral-clusteringCompare
Arjun-08/spectral-clustering4None declaredJupyter Notebook3 mo agospectral-clustering, graph-laplacianCompare
MehdiLotfian/PromptSplit5MITPython10 mo agospectral-clusteringCompare
UCD4IDS/NGWP.jl1None declaredJulia6 y agograph-laplacian, wavelets-on-graphsCompare

Read from GitHub and Hugging Face. A value a source does not give is shown as unknown, never guessed.

Get , open it once and sign in. Then come back here and press the button again.