ResearchDatasetsViLPFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSelf-evaluationViLP77AUROC36Multimodal UnderstandingViLP 80% (test)58.06Accuracy10Prior-Sensitive EvaluationViLP-F with-fact70.17Score8Language Shortcut RobustnessViLP59.3Accuracy6Uncertainty EstimationVILP0.521Verb-U2