{"id":"W4411083203","doi":"10.1016/j.neunet.2025.107673","title":"LaTP: LiDAR-aided multimodal token pruning for efficient trajectory prediction of autonomous driving","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Key Research and Development Projects of Shaanxi Province; National Natural Science Foundation of China","keywords":"Pruning; Security token; Computer science; Trajectory; Inference; Artificial intelligence; Lidar; Context (archaeology); Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0006777631,0.0001452086,0.0002421902,0.0001185155,0.0001703307,0.00007237134,0.0004530582,0.0001079643,0.000002212839],"category_scores_gemma":[0.0001054699,0.0001395969,0.0001312719,0.0004313977,0.00005119806,0.0001448283,0.0001338305,0.0001802927,5.510818e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004289572,"about_ca_system_score_gemma":0.00005065887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001107321,"about_ca_topic_score_gemma":0.000009557157,"domain_scores_codex":[0.998649,0.000141234,0.0003522468,0.000380688,0.0001405057,0.0003363115],"domain_scores_gemma":[0.9987915,0.000526661,0.0001329941,0.0003825401,0.0001169024,0.0000493703],"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":[0.00003488063,0.00007338785,0.02145967,0.00004827917,0.00004469357,0.000003140209,0.000323625,0.7819955,0.001238295,0.001157258,0.0005371014,0.1930842],"study_design_scores_gemma":[0.0004338323,0.0001024883,0.06990223,0.00006451971,0.00001052361,0.000002240208,0.000006990252,0.9277356,0.001175801,0.000164066,0.0003107934,0.00009089781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2178494,0.0001563582,0.7793655,0.0001219242,0.00166342,0.0002747262,0.000002427139,0.0002088884,0.0003573169],"genre_scores_gemma":[0.9550592,0.000004545362,0.04445098,0.0001279835,0.0002226461,0.00002902396,0.000004547158,0.00001019638,0.00009085745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7372098,"threshold_uncertainty_score":0.5692598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01735696868252264,"score_gpt":0.2748433309130945,"score_spread":0.2574863622305719,"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."}}