{"id":"W4405033244","doi":"10.1109/iccv51701.2025.01364","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-Driven Talking Portrait","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Portrait; Generative grammar; Matching (statistics); Float (project management); Flow (mathematics); Motion (physics); Computer science; Generative model; Acoustics; Speech recognition; Computer vision; Artificial intelligence; Art; Visual arts; Engineering; Marine engineering; Mathematics; Geometry; Physics","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":[0.0004540854,0.0006551448,0.0005202569,0.0005722209,0.0002437106,0.0005444283,0.0009513684,0.0006808278,0.005037365],"category_scores_gemma":[0.001621399,0.0003808409,0.0008362293,0.0004139289,0.0003625401,0.0007222401,0.0009087451,0.001110366,0.001362117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003444364,"about_ca_system_score_gemma":0.0003880036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001765815,"about_ca_topic_score_gemma":0.002453737,"domain_scores_codex":[0.9997451,0.0000481473,0.000008848396,0.00007199286,0.0001004304,0.00002553847],"domain_scores_gemma":[0.9997398,0.0001015878,0.00002938783,0.00005192332,0.00004363584,0.00003355095],"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":[0.0002828958,0.0001557014,0.0009201983,0.0002234921,0.0001125924,0.0003227803,0.00028879,0.2367107,0.07734771,0.01985562,0.01250521,0.6512744],"study_design_scores_gemma":[0.00002010955,0.0000329455,0.0001695069,0.000008255077,0.000009194487,0.0001114907,0.00001631607,0.9844065,0.008451989,0.003888697,0.002873225,0.00001175448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00416218,0.0001069739,0.9938614,0.0000496018,0.0000341559,0.0000428657,0.00007336524,0.001056874,0.0006125098],"genre_scores_gemma":[0.297646,0.0004151276,0.6907336,0.0002369437,0.0001389432,0.0002268416,0.001267354,0.001017862,0.008317376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005037365,"threshold_uncertainty_score":0.01685166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02837923795009671,"score_gpt":0.2749640554177935,"score_spread":0.2465848174676967,"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."}}