{"id":"W4413144838","doi":"10.1109/cvpr52734.2025.02200","title":"Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Natural Science Foundation of China; National Research Foundation","keywords":"Computer science; Sample (material); Image (mathematics); Artificial intelligence; Multimedia; Natural language processing; Human–computer interaction; Computer vision","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":[0.001155652,0.001058819,0.0005428872,0.0004005683,0.0002925628,0.0007225947,0.001223718,0.001099262,0.004083973],"category_scores_gemma":[0.00806041,0.000442189,0.0005116418,0.0002301194,0.0007012516,0.001897035,0.001209466,0.001691456,0.0008894781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007999315,"about_ca_system_score_gemma":0.0006184523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001139367,"about_ca_topic_score_gemma":0.002195109,"domain_scores_codex":[0.9996188,0.0001086566,0.00001556715,0.0001554978,0.00006273579,0.00003876931],"domain_scores_gemma":[0.9982286,0.00109495,0.0001348393,0.0002212906,0.0001846913,0.0001356349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006243308,0.0004365855,0.004959789,0.000396883,0.00007880385,0.0004575939,0.0006378446,0.5207853,0.04992284,0.03019416,0.008200437,0.3833054],"study_design_scores_gemma":[0.00003331478,0.00006558029,0.0003331191,0.00001470853,0.00001059101,0.00004932357,0.00002702255,0.9780768,0.006229334,0.01402899,0.001119142,0.00001202743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07962724,0.0004917962,0.9105462,0.0004192586,0.0001389479,0.0002007622,0.0002059464,0.004914459,0.003455458],"genre_scores_gemma":[0.8154945,0.0002039003,0.1781086,0.0003618443,0.00005295552,0.0002940316,0.000342422,0.0005926857,0.00454907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004083973,"threshold_uncertainty_score":0.01366222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01097425876069688,"score_gpt":0.2664345706546699,"score_spread":0.255460311893973,"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."}}