{"id":"W4413145832","doi":"10.1109/cvpr52734.2025.02749","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Representation (politics); Artificial intelligence; Object (grammar); Natural language processing; Programming language","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":[0.0002350383,0.0001047786,0.000133949,0.000220116,0.0002255574,0.0002071152,0.0004818926,0.00004758479,0.00008853023],"category_scores_gemma":[0.0003297591,0.0000987681,0.0000542415,0.0011823,0.00001647948,0.0002406827,0.0002086586,0.0002304836,0.0003195294],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005264531,"about_ca_system_score_gemma":0.0000726507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00130851,"about_ca_topic_score_gemma":0.00001903432,"domain_scores_codex":[0.9988384,0.0001354691,0.0001988113,0.0004066993,0.0001802495,0.0002403907],"domain_scores_gemma":[0.9991285,0.0002719427,0.000072551,0.0004027864,0.00007253633,0.0000516675],"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":[0.00003743211,0.0004025854,0.1454665,0.00005138277,0.000132835,0.0000188724,0.002607249,0.03697915,0.04863226,0.2642687,0.005892179,0.4955108],"study_design_scores_gemma":[0.0008121054,0.0000335343,0.04337724,0.00001060285,0.00001052608,0.000002818541,0.0001679507,0.9448538,0.006243128,0.0008091453,0.003521134,0.0001579824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1363631,0.0001520103,0.7896875,0.002736358,0.0001561267,0.0002902749,2.232272e-7,0.000808533,0.06980585],"genre_scores_gemma":[0.9680888,0.000005283884,0.01721012,0.0004553841,0.00003933334,0.00005514222,0.000006380391,0.000006441361,0.01413313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9078747,"threshold_uncertainty_score":0.410701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005370343066093995,"score_gpt":0.3115068523151343,"score_spread":0.3061365092490402,"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."}}