{"id":"W4416750391","doi":"10.1109/iros60139.2025.11246991","title":"Find Everything: A General Vision Language Model Approach to Multi-Object Search","year":2025,"lang":"","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Robustness (evolution); Language model; Reinforcement learning; Natural language; Leverage (statistics); Semantics (computer science)","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":[0.0008207662,0.0009881651,0.001284799,0.000840726,0.0004548224,0.001402821,0.00306066,0.001574773,0.003389896],"category_scores_gemma":[0.002283027,0.0006333077,0.001318056,0.0009867662,0.0007486324,0.002358045,0.001914498,0.002056584,0.001344657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201614,"about_ca_system_score_gemma":0.001582255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01393979,"about_ca_topic_score_gemma":0.01728262,"domain_scores_codex":[0.9995506,0.0001037876,0.00002514311,0.0001387421,0.0001164863,0.00006511274],"domain_scores_gemma":[0.9994298,0.0002501124,0.00006329557,0.00008395439,0.0001168555,0.00005602561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001778862,0.0001760173,0.0009965268,0.000183643,0.0001638136,0.0002332857,0.0002090781,0.7229738,0.005275474,0.04471886,0.009295312,0.2155963],"study_design_scores_gemma":[0.000007486492,0.00001884757,0.00003548366,0.000003798397,0.000005199553,0.00001923263,0.000009259151,0.9868191,0.0003278917,0.0121335,0.0006149658,0.000005305473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004758536,0.0003380633,0.990892,0.0002901268,0.00005023137,0.00004262772,0.0001727759,0.001897524,0.001558137],"genre_scores_gemma":[0.4439996,0.0006708581,0.5425599,0.000918453,0.0001424077,0.0003399265,0.00106569,0.000715292,0.009587808],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01393979,"threshold_uncertainty_score":0.02771729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02112816748585604,"score_gpt":0.2883843394690382,"score_spread":0.2672561719831822,"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."}}