{"id":"W4386566765","doi":"10.18653/v1/2023.eacl-main.185","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Samsung; Canadian Institute for Advanced Research","keywords":"Computer science; Adaptation (eye); Artificial intelligence; Computational linguistics; Association (psychology); Shot (pellet); Natural language processing; Speech recognition; Psychology; Neuroscience; Chemistry","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":[0.0005997588,0.0001414101,0.000178532,0.0002120596,0.0001482005,0.00007845464,0.0006411629,0.00005952225,0.000008221476],"category_scores_gemma":[0.0002003048,0.0001271134,0.00009126877,0.0007625641,0.00003461654,0.0001910502,0.000205034,0.0001049199,0.00002476567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003081949,"about_ca_system_score_gemma":0.00007258593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005109547,"about_ca_topic_score_gemma":0.00001406475,"domain_scores_codex":[0.9984959,0.00006515715,0.0003617328,0.0004646202,0.0003078497,0.0003047778],"domain_scores_gemma":[0.9984319,0.0005986953,0.0001722207,0.0005834356,0.0001360294,0.00007775396],"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":[0.0000109146,0.00009970641,0.00004109334,0.00004745056,0.00001140649,6.9663e-7,0.004864602,0.8980193,0.007824316,0.04171728,0.00007350539,0.04728977],"study_design_scores_gemma":[0.0003944791,0.0001217873,0.003117985,0.00002341698,0.000005834201,0.000001495289,0.0002844637,0.9914089,0.001303771,0.003157304,0.00003799047,0.0001425058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3577363,0.000006752836,0.6401752,0.0005825993,0.00004556214,0.0006157326,0.000008140525,0.0004288655,0.0004009446],"genre_scores_gemma":[0.7489352,5.325624e-7,0.2504884,0.00003561178,0.00002067624,0.0001999052,0.00002881525,0.00001445683,0.0002763882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.391199,"threshold_uncertainty_score":0.5183532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04356935763959081,"score_gpt":0.3403577905972081,"score_spread":0.2967884329576173,"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."}}