ResearchTasksAudio-to-(Text+Image) GenerationAudio-to-(Text+Image) GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedtriplet (text, image, audio)FlowBind36.79CLAP Score (A->T)3Feb 26, 2026