{"id":"W4409366792","doi":"10.1609/aaai.v39i7.32725","title":"FunEditor: Achieving Complex Image Edits via Function Aggregation with Diffusion Models","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Diffusion; Function (biology); Computer science; Image (mathematics); Computer graphics (images); Biological system; Computer vision; Physics; Biology; Thermodynamics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003766805,0.000218247,0.0002204509,0.0001945924,0.0003246162,0.0003229107,0.001328884,0.00009805561,0.00002293814],"category_scores_gemma":[0.0001174906,0.0001512816,0.0000836064,0.001033141,0.0002489142,0.001011209,0.0003096013,0.0002742603,0.00002334689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007814428,"about_ca_system_score_gemma":0.00009629853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002018742,"about_ca_topic_score_gemma":0.000004510443,"domain_scores_codex":[0.99824,0.00002159288,0.0004594826,0.000488304,0.00053563,0.0002550053],"domain_scores_gemma":[0.9980509,0.00007020609,0.0003872986,0.0003347488,0.001102652,0.00005414666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009386437,0.0001107807,0.00003885332,0.00004507758,0.00001057066,1.181312e-7,0.000206215,0.00001023444,0.2848146,0.5551012,0.0003996326,0.1591689],"study_design_scores_gemma":[0.0000309304,0.0001834432,0.0003137651,0.0002974391,0.00001676635,0.000001587584,0.0001498091,0.2081725,0.5977054,0.1926923,0.0002753888,0.0001606785],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005986391,0.00001752604,0.9769707,0.003801521,0.0007202029,0.0004375783,0.000002053329,0.0002450303,0.01181894],"genre_scores_gemma":[0.9887607,0.00003750578,0.0103208,0.0002341643,0.0001301055,0.00003960371,0.000001407493,0.000009359048,0.000466375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9827743,"threshold_uncertainty_score":0.6169086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05099039595220399,"score_gpt":0.2792226312104285,"score_spread":0.2282322352582245,"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."}}