{"id":"W7084073345","doi":"10.1109/infocomwkshps65812.2025.11152896","title":"AVLLM-Based Multimodal Reasoning Segmentation and Detection Approach for Intelligent Driving","year":2025,"lang":"en","type":"article","venue":"","topic":"Plant Ecology and Soil Science","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"Natural Science Foundation of Sichuan Province; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Segmentation; Encoder; Image segmentation; Opportunistic reasoning; Reasoning system; Model-based reasoning; Case-based reasoning; Text segmentation","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":[0.0007037011,0.001226119,0.0006961498,0.001710312,0.0005505182,0.001137796,0.001788093,0.0008951554,0.004149696],"category_scores_gemma":[0.001326589,0.0004571642,0.001613851,0.0007694953,0.0005301269,0.002020291,0.001795743,0.00099807,0.001779849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001060457,"about_ca_system_score_gemma":0.001484715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006810044,"about_ca_topic_score_gemma":0.01051825,"domain_scores_codex":[0.9991429,0.0001203231,0.00005121297,0.0002694343,0.0003152573,0.0001008745],"domain_scores_gemma":[0.9995902,0.00008808573,0.00004018734,0.00007387341,0.0001690244,0.00003875981],"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":[0.0003736349,0.0002440221,0.002258983,0.0003344,0.0001276358,0.0003549058,0.0004526628,0.05301499,0.08557055,0.01122579,0.005956205,0.8400862],"study_design_scores_gemma":[0.00003356089,0.0001422593,0.001204252,0.00002656351,0.00009431344,0.0002752178,0.0002922386,0.9376674,0.03845608,0.01153599,0.01021331,0.00005869014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008724965,0.0001766268,0.9847991,0.0001084285,0.00003851125,0.00008284065,0.000174479,0.003592079,0.002302923],"genre_scores_gemma":[0.2835121,0.0002404792,0.7086427,0.0003105231,0.00004684676,0.0002292562,0.001126232,0.000350599,0.005541275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006810044,"threshold_uncertainty_score":0.01388216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007376616670204438,"score_gpt":0.2351546691727393,"score_spread":0.2277780525025349,"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."}}