{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001391745,0.0007630912,0.0008507864,0.000953074,0.000541919,0.001309108,0.001900764,0.0002485496,0.00005377657],"category_scores_gemma":[0.000319937,0.0006035894,0.0001192388,0.001077501,0.0006366685,0.0004416425,0.001829199,0.0007237184,0.0001087779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002883558,"about_ca_system_score_gemma":0.0003997391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002582262,"about_ca_topic_score_gemma":0.00007342706,"domain_scores_codex":[0.9949856,0.00006440689,0.000547274,0.00234833,0.001021388,0.001033025],"domain_scores_gemma":[0.9965479,0.001337504,0.0002270804,0.001263806,0.000230716,0.0003929942],"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":[0.00003244355,0.00004301473,0.00000799293,0.00009166584,0.00004500842,0.0003220659,0.003713577,0.3704789,0.003975382,0.001498201,0.000297038,0.6194947],"study_design_scores_gemma":[0.0001834045,0.0002729346,0.00002459353,0.001907043,0.00003836524,0.0001070183,0.000003735433,0.9835278,0.002914387,0.004322313,0.005804046,0.0008943819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000436549,0.0006248414,0.9903388,0.001579666,0.0005921973,0.0005896094,0.000009828184,0.0002344984,0.005594034],"genre_scores_gemma":[0.1269507,0.00005421111,0.868175,0.001474322,0.0008471632,0.00004054101,0.000004364087,0.0001360537,0.002317668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6186004,"threshold_uncertainty_score":0.9997276,"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."}}