AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Explainable Mixture Models through Differentiable Rule Learning

Matthias Wilms, Sascha Xu, Jilles Vreeken

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add overlap penalty (lambda = 0.3) (ablation)XMM-GMM · Real datasetsnumber of rules: up to 16% fewer rules at λ = 0.3Improved
add overlap penalty (ablation)XMM-NSF · Real datasetsnumber of rules and NLL: rules only decrease significantly at λ = 1Mixed
use GMM instead of NSF density estimator (ablation)XMM · UCI real-world datasetsaverage rank of test NLL: 5.60 -> 4.20Improved
add BIC model selection (ablation)XMM-GMM · UCI real-world datasetsaverage rank of test NLL: 4.20 -> 4.47; rule rank 3.80 -> 1.73Mixed
add BIC model selection (ablation)XMM-NSF · UCI real-world datasetsaverage rank of test NLL: 5.60 -> 6.07Hurt
k-means++ anchoring instead of random initialization (ablation)XMM · synthetic datarule coverageImproved
replace CDTREE with XMMtree-based CDE · Gold nanoclusters HOMO-LUMOtest NLL: -1.683 -> -1.706Improved
increase initial number of rules k beyond true count (ablation)XMM-GMM vs XMM-NSF · synthetic dataexcess rulesMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy