{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001337221,0.001350067,0.0008599389,0.0005968781,0.0003827698,0.001387826,0.004863216,0.001432273,0.006109294],"category_scores_gemma":[0.005470377,0.0006829502,0.00124743,0.0007856513,0.001402194,0.004114306,0.003786949,0.002722396,0.001979479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001206478,"about_ca_system_score_gemma":0.001317889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004136589,"about_ca_topic_score_gemma":0.00591397,"domain_scores_codex":[0.9989704,0.0002545865,0.00004664821,0.0004302069,0.0001883616,0.0001097119],"domain_scores_gemma":[0.9982466,0.0007520901,0.0001468034,0.0005576806,0.0001808898,0.0001160002],"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":[0.0006758871,0.0006959973,0.001795561,0.000644242,0.0001291824,0.0002798325,0.0005563077,0.1499234,0.04196561,0.05137805,0.03140356,0.7205525],"study_design_scores_gemma":[0.00006023633,0.0001336658,0.0001459268,0.00001732064,0.00001642589,0.00007214345,0.00004903095,0.9530932,0.01187678,0.03002811,0.004476808,0.00003024482],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01020953,0.0002250154,0.9765286,0.0002341049,0.00004486231,0.0001345395,0.0004168629,0.0104359,0.001770702],"genre_scores_gemma":[0.4011182,0.000393169,0.5862349,0.0009943121,0.00007710645,0.0007603815,0.002868729,0.001344457,0.006208643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006109294,"threshold_uncertainty_score":0.02043766,"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."}}