ResearchDatasetsKling-AudioFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsVideo-and-Text-to-Audio GenerationKling-Audio (eval)2.1KL Divergence5Video-to-Audio GenerationKling-Audio-Eval2.47KL Divergence3Text-to-Audio GenerationKling-Audio Eval2.36KL Divergence3