{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001900365,0.00005232052,0.00008018676,0.0001239765,0.0001791388,0.0001936448,0.0001008817,0.00001868758,0.000005292918],"category_scores_gemma":[0.0002823424,0.00004514923,0.00002355029,0.0003406786,0.000004218386,0.0002012794,0.0001316232,0.00002417226,0.000008993761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002166461,"about_ca_system_score_gemma":0.00001335687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007818577,"about_ca_topic_score_gemma":0.0001412082,"domain_scores_codex":[0.9994854,0.00003537671,0.00007955168,0.0002447627,0.00006385321,0.00009101893],"domain_scores_gemma":[0.9996378,0.0001038454,0.00001571464,0.0001054875,0.00009590398,0.00004129035],"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":[0.00002401817,0.00004970806,0.008198383,0.00003278968,0.00006317973,6.963401e-7,0.003147073,0.008628424,0.05527901,0.08067364,0.007960445,0.8359426],"study_design_scores_gemma":[0.0002857092,0.0002669912,0.01143277,0.00001209283,0.00001775037,1.463878e-7,0.0000884456,0.9676977,0.009982999,0.001203344,0.008885906,0.0001260876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04417396,0.000004205433,0.9537066,0.001014201,0.00005949316,0.0004186774,9.375531e-7,0.00004367435,0.0005782028],"genre_scores_gemma":[0.7942248,0.00000137752,0.2031944,0.0008360609,0.00003561202,0.00008870322,0.000009393854,0.000002587825,0.001606998],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9590693,"threshold_uncertainty_score":0.1867321,"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."}}