{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005913945,0.0008209316,0.000411327,0.0004843398,0.0002100472,0.000569072,0.001198104,0.0005690888,0.005514282],"category_scores_gemma":[0.00248464,0.0002806869,0.0005023511,0.0003638288,0.0004325781,0.001263094,0.00144368,0.001175054,0.001817369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000455166,"about_ca_system_score_gemma":0.0004441809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001673113,"about_ca_topic_score_gemma":0.002611649,"domain_scores_codex":[0.9997641,0.00004338502,0.0000135557,0.00007458722,0.00007383723,0.00003039336],"domain_scores_gemma":[0.9995441,0.0002246764,0.00003193205,0.000078464,0.00007250674,0.00004821416],"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":[0.0006422821,0.0002446408,0.001387526,0.0003915,0.00008300273,0.0003613092,0.0002443113,0.1251453,0.147481,0.01753466,0.01395669,0.6925278],"study_design_scores_gemma":[0.00007893451,0.0001791228,0.0003680167,0.00002011449,0.00002749642,0.0002975945,0.00004699145,0.9147523,0.06693345,0.007542823,0.00972819,0.00002494286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02956024,0.0006871471,0.9562857,0.0001984229,0.0001952246,0.0001345406,0.0003876449,0.008589203,0.003961874],"genre_scores_gemma":[0.6228592,0.0005510214,0.3630581,0.0004076672,0.0001147355,0.0002525764,0.001827298,0.001440802,0.009488635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005514282,"threshold_uncertainty_score":0.01844716,"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."}}