{"id":"W4404654748","doi":"10.1007/978-3-031-72995-9_10","title":"PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Diffusion; Image (mathematics); Resource (disambiguation); Training (meteorology); Multimedia; Computer graphics (images); Artificial intelligence; Computer vision; Computer 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":[0.0005362657,0.001488075,0.00107006,0.0005421139,0.0003907961,0.001275346,0.002355082,0.001590784,0.0177695],"category_scores_gemma":[0.00239151,0.0005510739,0.0007994738,0.0005688039,0.0008018899,0.001393568,0.003176991,0.00231083,0.007147609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005363851,"about_ca_system_score_gemma":0.0007712395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002408299,"about_ca_topic_score_gemma":0.004557732,"domain_scores_codex":[0.999472,0.00007912364,0.0000214001,0.0001433105,0.0002314208,0.00005277897],"domain_scores_gemma":[0.9993668,0.000324979,0.0000269184,0.0001690803,0.00007536151,0.00003683796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003989794,0.0001821518,0.0002738977,0.0002728315,0.0001186826,0.0002170576,0.00015614,0.2029984,0.05729439,0.03570359,0.02817862,0.6742053],"study_design_scores_gemma":[0.00003649826,0.00005904674,0.00004802078,0.00001621447,0.00001459854,0.00007497525,0.00002017766,0.9526387,0.01919622,0.01836632,0.009515245,0.00001389621],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003454582,0.0004002344,0.9795389,0.000114296,0.0001551759,0.00005398116,0.0001351681,0.009991852,0.006155834],"genre_scores_gemma":[0.1390689,0.0004925699,0.834435,0.0004694325,0.0001366308,0.0002133977,0.0009157333,0.003610308,0.02065786],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0177695,"threshold_uncertainty_score":0.05944484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008880837916798421,"score_gpt":0.2145408104776294,"score_spread":0.205659972560831,"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."}}