ResearchBenchmarksStepwise validity estimation on Multi Sofa ScenarioFollow99.9Mean Inclusion Rate (Final)GMM98.96499.20799.4599.693Mar 4, 2026Evaluation ResultsMethodMethodLinksMean Inclusion Rate (Final)Mean Inclusion Rate (All)Success Rate (Final)Success Rate (All)Compactness (Final)GMMModel=GMMModel=GMM2026.0399.999.8100995.58Ellip-2Model=Ellip-2, K=2Model=Ellip-2, K=22026.0399.999.710099.44.6Ellip-1Model=Ellip-1, K=1Model=Ellip-1, K=12026.039998.910097.94.05