ResearchTasksAudio-visual temporal groundingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedVUE (TR)OmniAgent46.1Vision Score7Jun 18, 2026LongVALEOmniAgent39.1IoU3Jun 18, 2026