{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001061538,0.0005739561,0.0006758947,0.00171066,0.0002231113,0.000577838,0.002152232,0.0003363476,0.0000314288],"category_scores_gemma":[0.0001010549,0.0005299618,0.0002561065,0.0008925386,0.0002738565,0.0006454657,0.0004611944,0.0005338971,0.00005179866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002451629,"about_ca_system_score_gemma":0.0004156918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001185886,"about_ca_topic_score_gemma":0.00009425129,"domain_scores_codex":[0.9957989,0.00002563098,0.0008143894,0.001715988,0.0009358043,0.0007093215],"domain_scores_gemma":[0.9978722,0.0003219644,0.000193446,0.0009088497,0.0004300556,0.0002734903],"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":[0.000008660242,0.0000264778,0.000001483956,0.0001084375,0.00001267652,0.00001064712,0.002696173,0.001426905,0.04023046,0.0186256,0.0001619466,0.9366905],"study_design_scores_gemma":[0.0005085519,0.001378903,0.00002094448,0.002109512,0.00004310556,0.00007086025,0.000002564424,0.6120724,0.228572,0.1398744,0.01379111,0.001555612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000181932,0.0001128372,0.9905765,0.001856075,0.001240699,0.001536858,0.00004458433,0.0003281849,0.004122354],"genre_scores_gemma":[0.09138771,0.00002404665,0.9053147,0.001319593,0.0007212549,0.0001339444,0.00002228207,0.00007619971,0.001000306],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9351349,"threshold_uncertainty_score":0.9997152,"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."}}