amazon-science/muss v1.0.0
amazon-science/muss
Captured source
source ↗published Aug 4, 2026seen 3wcaptured 3whttp 200method plain
MUSS v1.0.0 — UAI 2026 release
Repository: amazon-science/muss
Tag: v1.0.0
Published: 2026-08-04T01:08:54Z
Prerelease: no
Release notes: First tagged release of MUSS: Multilevel Subset Selection for Relevance and Diversity (UAI 2026).
- Core MUSS algorithm (
src/methods/muss.py): partition → select-clusters → select-within, up to 80× faster than MMR with a constant-factor approximation guarantee - RAG and candidate-retrieval experiment runners with DPP, MMR, DGDS, clustering, and random baselines
- One-click Colab demo and local quick-start notebook
- Paper: https://arxiv.org/abs/2503.11126
Notability
notability 5.0/10Initial release of a text simplification model.