{"id":"W4400104527","doi":"10.48550/arxiv.2406.18043","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Vlaamse regering; Mitacs; Fonds Wetenschappelijk Onderzoek","keywords":"Embodied cognition; Foundation (evidence); Generalist and specialist species; Computer science; Artificial intelligence; Geography; Ecology; Biology; Archaeology; Habitat","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001464776,0.0008165883,0.000833461,0.0004370325,0.0004167,0.001556319,0.002001355,0.001527374,0.00738152],"category_scores_gemma":[0.005885498,0.0006525745,0.00142262,0.0004186793,0.001400832,0.002553314,0.003075472,0.002821566,0.001466395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132361,"about_ca_system_score_gemma":0.001109025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004200907,"about_ca_topic_score_gemma":0.005623787,"domain_scores_codex":[0.9993407,0.0002936687,0.00003408945,0.000148389,0.0001230957,0.00006003696],"domain_scores_gemma":[0.99866,0.0008503865,0.0001068656,0.0002084003,0.00009922877,0.00007508654],"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":[0.00005317945,0.0000397522,0.0004137931,0.00009414681,0.00003927686,0.00009538357,0.0001810047,0.8031537,0.001251141,0.1540354,0.003343612,0.03729955],"study_design_scores_gemma":[0.00001177469,0.00001012102,0.00003610132,0.00001180042,0.000003991144,0.00001261692,0.00001024786,0.9276721,0.0002231592,0.07031278,0.001688982,0.000006358445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003873958,0.0001219545,0.9920871,0.0003352162,0.00002666221,0.00003488735,0.0001713723,0.0009443949,0.002404517],"genre_scores_gemma":[0.4669329,0.0004859133,0.520558,0.0005654775,0.0000849514,0.0007908941,0.001054258,0.001042241,0.008485469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00738152,"threshold_uncertainty_score":0.02469367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1369722439224506,"score_gpt":0.2332615442925057,"score_spread":0.09628930037005509,"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."}}