{"id":"W4402670803","doi":"10.18653/v1/2024.findings-acl.66","title":"CoLLaVO: Crayon Large Language and Vision mOdel","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Ministry of Science and ICT, South Korea","keywords":"Computer science; Artificial intelligence; Human–computer interaction; Computer vision","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008239881,0.001173786,0.0006172654,0.000420398,0.0004012716,0.001494176,0.003603526,0.001141905,0.01615822],"category_scores_gemma":[0.003541504,0.0006652643,0.0009532751,0.0002951678,0.0008339484,0.003344715,0.002223598,0.002360222,0.004372629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200516,"about_ca_system_score_gemma":0.002252618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008586987,"about_ca_topic_score_gemma":0.01230026,"domain_scores_codex":[0.9996196,0.00008091753,0.00002036288,0.0001333232,0.00008622494,0.00005945639],"domain_scores_gemma":[0.9990805,0.0003673016,0.00005162176,0.0002609364,0.0001502549,0.00008932472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00182823,0.0006576819,0.00492427,0.001308359,0.0001617087,0.0004568632,0.0008874346,0.1761981,0.03569099,0.1451654,0.1796807,0.4530402],"study_design_scores_gemma":[0.0001763507,0.0002366256,0.0003904244,0.00006343004,0.00003864539,0.0001522669,0.00008738023,0.8901975,0.01539008,0.05356384,0.0396404,0.00006311011],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03917902,0.0008327896,0.7766694,0.0009568983,0.0003005308,0.0005489477,0.002597486,0.1566117,0.02230326],"genre_scores_gemma":[0.2999298,0.0003755059,0.6679726,0.0007211582,0.00006369979,0.001018851,0.005238803,0.007429034,0.01725058],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01615822,"threshold_uncertainty_score":0.05405462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00914918910983499,"score_gpt":0.3375273162868338,"score_spread":0.3283781271769988,"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."}}