{"id":"W4412106036","doi":"10.1016/j.cviu.2025.104442","title":"FedVLP: Visual-aware latent prompt generation for Multimodal Federated Learning","year":2025,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Machine learning","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003476711,0.0002157026,0.000215827,0.0002598843,0.001129595,0.001172578,0.0002608515,0.00008568257,0.000004743309],"category_scores_gemma":[0.00004621743,0.0002015987,0.00007162293,0.0003676571,0.0000511254,0.0004886826,0.000329621,0.0002407562,0.000008139435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001881802,"about_ca_system_score_gemma":0.00005236478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002357933,"about_ca_topic_score_gemma":0.000004237028,"domain_scores_codex":[0.9984754,0.0001132825,0.0002945836,0.0006591221,0.0001641839,0.0002933802],"domain_scores_gemma":[0.9992314,0.0002161613,0.0001098498,0.0002120892,0.0001349713,0.00009550161],"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":[0.0001292159,0.0006896228,0.003725811,0.0005015236,0.0002517152,0.00002373549,0.002942399,0.01516703,0.1599196,0.2499882,0.02088547,0.5457758],"study_design_scores_gemma":[0.0009530978,0.0001765723,0.001172321,0.00007850927,0.00000934166,0.000005574674,0.0000449562,0.9942533,0.0009722817,0.001383933,0.0007375023,0.0002126436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01546708,0.00006064815,0.9808171,0.002153737,0.0003089758,0.000585866,0.000001358961,0.0003855975,0.000219577],"genre_scores_gemma":[0.8427351,0.00001762801,0.1565951,0.0003344515,0.00009210228,0.00004039039,0.00003330498,0.00001458582,0.0001374167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9790862,"threshold_uncertainty_score":0.9998643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03252975693327115,"score_gpt":0.3306209197960363,"score_spread":0.2980911628627652,"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."}}