{"id":"W4405174106","doi":"10.1109/iccv51701.2025.01497","title":"LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian University Press; European Commission","keywords":"Merge (version control); Computer science; Artificial intelligence; Style (visual arts); Art; Information retrieval; Visual arts","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001978114,0.001867023,0.000952817,0.001727907,0.000692224,0.001220995,0.00234661,0.001753313,0.007809465],"category_scores_gemma":[0.004937748,0.0008753651,0.001809121,0.001101455,0.00083989,0.002934919,0.0021508,0.002367144,0.004827914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001202462,"about_ca_system_score_gemma":0.0008521147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004585929,"about_ca_topic_score_gemma":0.01063576,"domain_scores_codex":[0.9990702,0.0002595909,0.0000446099,0.0003488825,0.0001769019,0.00009979435],"domain_scores_gemma":[0.9984674,0.0005987998,0.0001505883,0.0004397544,0.0002234587,0.0001199928],"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":[0.0005306401,0.0003955315,0.00279392,0.0002402791,0.00027073,0.000234889,0.0003049952,0.1718444,0.02101889,0.007227999,0.01920578,0.775932],"study_design_scores_gemma":[0.00005113803,0.0001426761,0.0005087727,0.00002094126,0.00004384015,0.0001554657,0.00005603654,0.9768103,0.009973246,0.007583903,0.004623086,0.00003047133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03571452,0.0008313772,0.9374695,0.0003808216,0.0001707101,0.0003456015,0.0008414873,0.01942345,0.004822459],"genre_scores_gemma":[0.3143194,0.0005171206,0.6601871,0.0007971456,0.0002493133,0.0006202401,0.003620591,0.002289885,0.01739913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007809465,"threshold_uncertainty_score":0.02612525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02716344502001248,"score_gpt":0.294603943127127,"score_spread":0.2674404981071145,"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."}}