{"id":"W4404625217","doi":"10.1007/978-3-031-73411-3_5","title":"PIXART-$$\\Sigma $$: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Transformer; Sigma; Artificial intelligence; Computer vision; Electrical engineering; Physics; Quantum mechanics; Voltage","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":[0.0005038648,0.001079028,0.0005259013,0.0004965418,0.0003816177,0.0006752303,0.001239822,0.001001286,0.02452225],"category_scores_gemma":[0.001056335,0.0004627324,0.0005236339,0.0004163599,0.0004150981,0.0009567869,0.001212773,0.00154105,0.009434743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004857042,"about_ca_system_score_gemma":0.0008045108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003786425,"about_ca_topic_score_gemma":0.008935104,"domain_scores_codex":[0.999761,0.0000403164,0.00001325753,0.0000658592,0.00007717549,0.00004232156],"domain_scores_gemma":[0.9997458,0.00008277281,0.00001171995,0.00006725084,0.00006550767,0.00002701588],"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":[0.0004061155,0.0001253922,0.0004419122,0.0001484923,0.00005710057,0.0001133744,0.00006772149,0.03830708,0.05487341,0.008164566,0.03186525,0.8654298],"study_design_scores_gemma":[0.00005070508,0.0001607308,0.0003987621,0.00002706634,0.00002561292,0.0002204569,0.00002975211,0.8848321,0.09016544,0.005849741,0.01821219,0.00002735383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0187116,0.0005249041,0.9444055,0.0002286003,0.0003123293,0.0001075459,0.0004783027,0.02544153,0.009789704],"genre_scores_gemma":[0.2559302,0.0003410925,0.7034806,0.0004221477,0.00009343648,0.0001742245,0.003195378,0.003505794,0.03285712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02452225,"threshold_uncertainty_score":0.08203506,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03174797090960109,"score_gpt":0.2780515632484664,"score_spread":0.2463035923388653,"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."}}