{"id":"W4405491040","doi":"10.1109/me61309.2024.10789747","title":"Human 0, MLLM 1: Unlocking New Layers of Automation in Language-Conditioned Robotics with Multimodal LLMs","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Automation; Robotics; Artificial intelligence; Computer science; Natural language processing; Engineering; Robot; Mechanical engineering","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":[0.001543219,0.001074989,0.0004569037,0.0003443612,0.0003850312,0.001300243,0.00143491,0.001053228,0.005909111],"category_scores_gemma":[0.005556394,0.0003778603,0.0006033823,0.0001734862,0.001784662,0.003007139,0.003114783,0.001800028,0.001757254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006738324,"about_ca_system_score_gemma":0.001245958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002516952,"about_ca_topic_score_gemma":0.003828713,"domain_scores_codex":[0.9989114,0.0004194938,0.00004444256,0.0002584848,0.0002632596,0.0001029826],"domain_scores_gemma":[0.9982054,0.0008922048,0.0001328847,0.0004262294,0.0002139344,0.0001293055],"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":[0.001617858,0.0006957812,0.00363438,0.0008859631,0.0001307344,0.000575634,0.001949274,0.1673456,0.1687182,0.03461982,0.01355909,0.6062676],"study_design_scores_gemma":[0.00007618691,0.0007455169,0.0009238815,0.00007671821,0.00004287705,0.0002134694,0.0002928436,0.8980533,0.05892079,0.027284,0.01324863,0.0001218861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05832004,0.0002467151,0.9122381,0.0005443923,0.0001221792,0.0001849994,0.0001917191,0.02085222,0.007299765],"genre_scores_gemma":[0.5767055,0.0001144986,0.4163159,0.0005528761,0.00003949089,0.000251505,0.0003654319,0.0008702674,0.004784655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005909111,"threshold_uncertainty_score":0.01976794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009887768186568531,"score_gpt":0.2855540961170812,"score_spread":0.2756663279305126,"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."}}