{"id":"W4409093780","doi":"10.1109/iccv51701.2025.01451","title":"VPO: Aligning Text-to-Video Generation Models with Prompt Optimization","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science","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":[0.002329426,0.002102039,0.001378452,0.000809396,0.0004683609,0.001306626,0.002718527,0.001887736,0.004014714],"category_scores_gemma":[0.008270041,0.0007943132,0.001269977,0.0006676125,0.0009061201,0.002135731,0.002194574,0.003035687,0.001464706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162809,"about_ca_system_score_gemma":0.001772714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005740955,"about_ca_topic_score_gemma":0.007151966,"domain_scores_codex":[0.9986176,0.0004361445,0.00007315077,0.000524982,0.0002171082,0.0001310246],"domain_scores_gemma":[0.9977542,0.001290465,0.0001602189,0.0003301768,0.0003166625,0.0001483605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005090925,0.0004378875,0.002389864,0.0004619548,0.0001063324,0.0003288472,0.0003844338,0.5134999,0.01540095,0.008513569,0.01871979,0.4392475],"study_design_scores_gemma":[0.00006435234,0.000102861,0.0001601104,0.00001572594,0.00001697279,0.00003642585,0.00002929052,0.9890825,0.002970765,0.005617741,0.001888726,0.00001452577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02121394,0.0008677462,0.962913,0.0003675778,0.0001799274,0.0002999254,0.0004892836,0.01155282,0.002115871],"genre_scores_gemma":[0.4255518,0.0005799384,0.5588008,0.001074951,0.0002371031,0.0007779403,0.00364141,0.00211243,0.007223599],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005740955,"threshold_uncertainty_score":0.01343054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02821746942137299,"score_gpt":0.246712028854658,"score_spread":0.2184945594332851,"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."}}