{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000160377,0.0003710754,0.000320837,0.0002012323,0.0002239999,0.0002929438,0.001005618,0.0001909958,0.00004191959],"category_scores_gemma":[0.00001980109,0.0003266025,0.0001896742,0.0004940912,0.000130923,0.0002630606,0.003245603,0.0006795884,0.0001159106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001748596,"about_ca_system_score_gemma":0.0001808975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002310344,"about_ca_topic_score_gemma":0.0001040353,"domain_scores_codex":[0.9979075,0.0001549192,0.0001519172,0.001303244,0.0001170527,0.0003653474],"domain_scores_gemma":[0.9987115,0.00009115252,0.0001323173,0.0007784556,0.0001416435,0.0001449936],"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":[0.00005194214,0.0001127289,0.001355272,0.0001021837,0.000264455,0.000904039,0.002053084,0.9586685,0.000304988,0.03143124,0.000618934,0.004132609],"study_design_scores_gemma":[0.0002498319,0.0001068167,0.001641562,0.0002873689,0.0001110369,0.00000862569,0.0002220894,0.9809771,0.0002122705,0.01541585,0.0002381957,0.0005292425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.230912,0.0001468841,0.7641948,0.0001591149,0.0006487226,0.0002362408,0.00001036468,0.0002759543,0.003415869],"genre_scores_gemma":[0.9926112,0.0001091124,0.004563356,0.00006338489,0.0002030484,0.000001143348,0.000008562414,0.00002595116,0.002414256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7616992,"threshold_uncertainty_score":0.9999186,"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."}}