{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001084719,0.001330169,0.001031427,0.0004786229,0.0005724009,0.002312573,0.003101812,0.001458654,0.005824696],"category_scores_gemma":[0.003662842,0.0006584646,0.001488993,0.0005190565,0.001222589,0.00523336,0.002282205,0.003279209,0.003630608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001422844,"about_ca_system_score_gemma":0.002571089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007726752,"about_ca_topic_score_gemma":0.01279715,"domain_scores_codex":[0.999276,0.0001407644,0.00003961572,0.0003487715,0.00009203389,0.0001027575],"domain_scores_gemma":[0.9990397,0.000264504,0.0000614723,0.0004190918,0.0001196399,0.00009548579],"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":[0.0008656543,0.0004463577,0.004030977,0.0008508632,0.0002110888,0.0003722802,0.0007513478,0.242646,0.04461756,0.06027022,0.05659965,0.588338],"study_design_scores_gemma":[0.00003843749,0.0001027866,0.0003221123,0.00003834654,0.00004068564,0.00008432334,0.00009527907,0.9310799,0.01369614,0.04442712,0.01004214,0.00003265633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04834696,0.001440764,0.903467,0.001511466,0.0002741344,0.0003056099,0.00159757,0.03503687,0.008019627],"genre_scores_gemma":[0.442667,0.0007834652,0.5355827,0.001642805,0.0001020713,0.0004977681,0.004547911,0.002074244,0.01210211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007726752,"threshold_uncertainty_score":0.01948553,"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."}}