Skip to content

MUSS v1.0.0 — UAI 2026 release

Latest

Choose a tag to compare

@ntienvu ntienvu released this 04 Aug 01:08
· 1 commit to main since this release

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