{"id":"W4402728164","doi":"10.1109/cvpr52733.2024.01335","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Human–computer interaction; Artificial intelligence; Natural language processing; Computer graphics (images); Programming language; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003218813,0.0001516556,0.0002138883,0.0002296333,0.00003152218,0.00007711741,0.0007845397,0.00005468368,0.00007307062],"category_scores_gemma":[0.00003077947,0.0001292683,0.00008013156,0.0004723323,0.00003294447,0.0002072227,0.0004061745,0.0001558508,0.0001433503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002480208,"about_ca_system_score_gemma":0.00005886591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004265622,"about_ca_topic_score_gemma":0.00001365515,"domain_scores_codex":[0.9986258,0.00005331777,0.0003663065,0.0004399987,0.0002924721,0.0002221089],"domain_scores_gemma":[0.9988754,0.0001055227,0.00007153252,0.000760525,0.00007436785,0.0001126811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001077608,0.0001485443,0.0001952002,0.0001524884,0.00005431287,0.00001522435,0.004806331,0.2112069,0.5686623,0.1288513,0.005285904,0.08061059],"study_design_scores_gemma":[0.0001241258,0.00006797491,0.000353599,0.00005678342,0.00001084836,0.000005355753,0.00001646325,0.9766366,0.02097583,0.001192914,0.000422924,0.0001365175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09770814,0.0001528345,0.8971252,0.001702044,0.00005995939,0.0002601017,0.000008781683,0.0002101799,0.002772784],"genre_scores_gemma":[0.5711043,0.000001585186,0.4271431,0.000197587,0.00001858365,0.0000182905,0.000004218901,0.000013994,0.001498341],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7654297,"threshold_uncertainty_score":0.5271409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02613095725492228,"score_gpt":0.321294885700474,"score_spread":0.2951639284455518,"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."}}