{"id":"W4413145840","doi":"10.1109/cvpr52734.2025.00877","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Security token; Pruning; Diversity (politics); Artificial intelligence; Computer network; Biology","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":[0.0003152252,0.0001490888,0.0001582296,0.0001858699,0.0007898975,0.0001276792,0.001041263,0.00007509148,0.00001502013],"category_scores_gemma":[0.00006351231,0.000146875,0.0001045539,0.0004342494,0.00001961799,0.0003526785,0.001127524,0.0001602282,0.00002587514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000061968,"about_ca_system_score_gemma":0.0001034938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004806644,"about_ca_topic_score_gemma":0.00002882432,"domain_scores_codex":[0.9987365,0.00004717031,0.0001821066,0.0004808399,0.0001932473,0.0003601134],"domain_scores_gemma":[0.998937,0.0003107693,0.00005994898,0.0004806714,0.0001302237,0.00008138021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002627553,0.0003839016,0.01433103,0.00005827161,0.00004447984,0.000001339319,0.000496649,0.07624512,0.0005451514,0.8905915,0.001952862,0.0153234],"study_design_scores_gemma":[0.001107091,0.00003112195,0.004722759,0.00001267986,0.00001028617,1.79134e-7,0.00001684931,0.9859642,0.0005176318,0.005446577,0.002010888,0.0001596763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01931303,0.00001421121,0.9717262,0.003435084,0.0001243699,0.0005208913,0.000008560347,0.0005527451,0.004304955],"genre_scores_gemma":[0.7514797,3.739498e-7,0.2462035,0.001443927,0.00001798178,0.00008150303,0.00001287722,0.000006469971,0.0007536227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9097192,"threshold_uncertainty_score":0.6075333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01616403560729983,"score_gpt":0.3084121409683172,"score_spread":0.2922481053610174,"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."}}