ResearchTasksMulti-shot Audio-Visual GenerationMulti-shot Audio-Visual GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMAVINSet high-fidelity benchmark 1K-sample (test)MAVIN231.6FVD11Jun 30, 2026MAVINSet subjective 20 samplesMAVIN36.8AVQ11Jun 30, 2026