{"id":"W4410196438","doi":"10.1007/s44196-025-00853-0","title":"Dual Adapter Tuning of Vision–Language Models Using Large Language Models","year":2025,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Adapter (computing); Language model; Dual (grammatical number); Artificial intelligence; Natural language processing; Linguistics; Computer hardware","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0009797689,0.0001976134,0.0003591448,0.0008071434,0.00009679285,0.000238009,0.001579033,0.00008551079,0.00001653542],"category_scores_gemma":[0.000116087,0.0001855257,0.0002022811,0.0004623767,0.00006624246,0.001135126,0.0003324776,0.000350913,0.000007483046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001869254,"about_ca_system_score_gemma":0.0003480388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004224057,"about_ca_topic_score_gemma":0.000004895651,"domain_scores_codex":[0.9968865,0.0001875302,0.001254987,0.0002844942,0.001167173,0.0002192984],"domain_scores_gemma":[0.9963543,0.0005439515,0.0009557193,0.0002923824,0.001760029,0.00009362878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001965681,0.0001072332,0.00009840056,0.00001853538,0.0001385782,0.00002860273,0.002246652,0.7529647,0.0007851245,0.2389219,0.00004466196,0.004626004],"study_design_scores_gemma":[0.0002523604,0.0000450995,0.0002392379,0.000421853,0.00001584013,0.0002030345,0.0008541123,0.963013,0.0004186688,0.03434312,0.0000557893,0.0001378788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07204293,0.0008536196,0.9243035,0.0004748459,0.001116133,0.0001596839,0.0000258739,0.00003907768,0.0009843643],"genre_scores_gemma":[0.9201595,0.00001036141,0.07939022,0.0001352266,0.0001810231,0.000005072152,0.00001040408,0.00001276712,0.00009544808],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8481165,"threshold_uncertainty_score":0.756552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02969291641567239,"score_gpt":0.364484520778666,"score_spread":0.3347916043629936,"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."}}