{"id":"W4389285856","doi":"10.1007/978-3-031-48796-5_10","title":"StableYolo: Optimizing Image Generation for Large Language Models","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Image (mathematics); Inference; Process (computing); Artificial intelligence; Computation; Bounded function; Approx; Baseline (sea); Image quality; Computer vision; Algorithm; Programming language; Operating system; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001266573,0.0004381765,0.000414911,0.0007068659,0.0004693097,0.0007271974,0.002615636,0.0002632142,0.000009425294],"category_scores_gemma":[0.0001438928,0.0004349012,0.0001386921,0.0005873291,0.0001553406,0.0008021867,0.00115367,0.0006617069,0.00007055571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002379413,"about_ca_system_score_gemma":0.0003363944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008184763,"about_ca_topic_score_gemma":0.00009217717,"domain_scores_codex":[0.9964741,0.00003251271,0.0004573109,0.00162566,0.0006644436,0.000745967],"domain_scores_gemma":[0.9972903,0.0005190783,0.0002682817,0.001503955,0.0002770543,0.0001413985],"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":[0.000003336412,0.0000329451,0.000005200283,0.0000572105,0.00001405043,0.00002296615,0.002474148,0.613543,0.003728611,0.1919205,0.00009837249,0.1880996],"study_design_scores_gemma":[0.0002517295,0.00005427451,0.00001034181,0.00007897933,0.00000636907,0.000008752293,3.817556e-7,0.922767,0.0009109441,0.07527845,0.0002044262,0.0004283814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008965445,0.0001325856,0.9951405,0.001092252,0.000839685,0.0008138583,0.00004007321,0.0005328081,0.001318608],"genre_scores_gemma":[0.05616044,0.00001962127,0.9414815,0.0007438355,0.0006090126,0.00009936286,0.00006262852,0.00007186899,0.0007516966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3092239,"threshold_uncertainty_score":0.9998103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02895945149165552,"score_gpt":0.2932319525451203,"score_spread":0.2642725010534648,"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."}}