{"id":"W4404397123","doi":"","title":"Boosting Latent Diffusion with Perceptual Objectives","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Artificial intelligence; Generative model; Boosting (machine learning); Autoencoder; Pattern recognition (psychology); Margin (machine learning); Generative grammar; Machine learning; Artificial neural network","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":[0.001539552,0.001083696,0.001172056,0.0007076754,0.0003172074,0.00109551,0.0008186729,0.001796031,0.005159804],"category_scores_gemma":[0.005762566,0.0005766494,0.0006729862,0.0005494067,0.0009376491,0.001362911,0.001833662,0.002235817,0.001502905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007478099,"about_ca_system_score_gemma":0.0004254813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001600077,"about_ca_topic_score_gemma":0.001569832,"domain_scores_codex":[0.9996356,0.0001227986,0.00001078294,0.0001124955,0.00008337138,0.00003492571],"domain_scores_gemma":[0.9983183,0.001070764,0.00009642114,0.0001538556,0.000234749,0.0001259118],"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":[0.0001877639,0.0001270101,0.0005725436,0.0002055596,0.00008177617,0.00006689498,0.00007008568,0.7451226,0.01563747,0.0506388,0.007449903,0.1798395],"study_design_scores_gemma":[0.000007437036,0.00001445949,0.00005641132,0.000007365402,0.000005765814,0.00001215196,0.000002391791,0.9878522,0.001236914,0.01014277,0.0006582575,0.000003807425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01359716,0.0006288736,0.9801692,0.0008833501,0.0002224915,0.00003413593,0.00006797142,0.0005250153,0.0038717],"genre_scores_gemma":[0.7182835,0.001289355,0.2519838,0.0009313773,0.000821699,0.0001157721,0.0003375723,0.0005902409,0.02564669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005159804,"threshold_uncertainty_score":0.01726121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04491176319787862,"score_gpt":0.1726105576442591,"score_spread":0.1276987944463805,"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."}}