{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003648748,0.0003740698,0.0003691124,0.0004764082,0.0001921457,0.0002596418,0.0002935655,0.0003017061,0.00006225724],"category_scores_gemma":[0.00006307692,0.0003776856,0.0001496054,0.000861299,0.00002713485,0.0001515649,0.0001837464,0.0003917351,0.00008488894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002512318,"about_ca_system_score_gemma":0.0001451238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003645806,"about_ca_topic_score_gemma":0.00002465925,"domain_scores_codex":[0.9978024,0.00008525408,0.0004886726,0.0006076964,0.0003845922,0.0006314043],"domain_scores_gemma":[0.99899,0.00004987604,0.00002202411,0.0005841987,0.0001283796,0.0002255282],"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":[0.0000278805,0.0002303065,0.00004876838,0.0002710386,0.00006697144,0.000004915667,0.003232001,0.9666566,0.01789026,0.005396337,0.0020218,0.004153162],"study_design_scores_gemma":[0.0008288932,0.00004750567,0.0002604287,0.0001029134,0.00004043677,0.000001513231,0.0005166565,0.9903278,0.007332519,0.00002802047,0.0001155876,0.0003977689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08267648,0.0003343369,0.8918669,0.0002100085,0.0002943314,0.0006298053,0.00001471831,0.0001753637,0.02379803],"genre_scores_gemma":[0.7668353,0.00004994691,0.2011937,0.0005077797,0.00008599467,0.0000141474,0.00005540002,0.00006231318,0.03119549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6906732,"threshold_uncertainty_score":0.9998675,"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."}}