{"id":"W4415537863","doi":"10.1145/3746027.3755713","title":"AV-DiT: Taming Image Diffusion Transformers for Efficient Joint Audio and Video Generation","year":2025,"lang":"","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformer; Joint (building); Block (permutation group theory); Feature (linguistics); Audio signal; Feature extraction","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007610074,0.000341056,0.0003814003,0.0002620947,0.001161896,0.0009727892,0.0002560898,0.0001493677,0.00006840201],"category_scores_gemma":[0.0000765677,0.000302114,0.000161355,0.0005192416,0.0001682405,0.0005400674,0.0002067962,0.0001765255,0.00000699943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001130334,"about_ca_system_score_gemma":0.0002852967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003056863,"about_ca_topic_score_gemma":0.00002047045,"domain_scores_codex":[0.9974386,0.00005779406,0.0006592222,0.0009539761,0.0003156488,0.0005747689],"domain_scores_gemma":[0.9991306,0.00009515014,0.000160687,0.0002559481,0.0002029131,0.0001546997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000171092,0.0001185932,0.00001589565,0.0004769501,0.00002614477,0.000002419896,0.001992265,0.0003786245,0.2492835,0.004611969,0.004405089,0.7386714],"study_design_scores_gemma":[0.00116886,0.00009469499,0.0003415418,0.0003252181,0.00005747582,0.000005258943,0.0001454647,0.8794535,0.1132725,0.000294438,0.004515808,0.0003252649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08304726,0.0009868746,0.9017927,0.007329336,0.00151697,0.0007443833,0.00000500953,0.00008082024,0.004496627],"genre_scores_gemma":[0.9309662,0.0001824792,0.06133126,0.003041649,0.0002934324,0.00005415724,0.000006880763,0.00001704326,0.004106904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8790749,"threshold_uncertainty_score":0.9999431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026661681836029,"score_gpt":0.2548370937974336,"score_spread":0.2345704769790734,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}