ResearchBenchmarksLoss-driven active learning on Benchmark functions out-of-distributionFollow0.05Weighted RMSEPOLAR0.02240.20870.3950.5813Jun 23, 2026Evaluation ResultsMethodMethodLinksWeighted RMSEWeighted NLPDPOLARbackbone=TabICLv2, lay...backbone=TabICLv2, layer=last layer2026.060.051.68GP-VRω2026.060.150.83GP-VR2026.060.333.3GP-US2026.060.454.2GP-RS2026.060.743.09