{"id":"W4402903985","doi":"10.1109/cvprw63382.2024.00765","title":"ATOM: Attention Mixer for Efficient Dataset Distillation","year":2024,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Bank of Canada; University of Toronto","funders":"","keywords":"Distillation; Atom (system on chip); Computer science; Atom optics; Atomic physics; Physics; Chemistry; Parallel computing; Chromatography","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":[0.00007245272,0.0000425723,0.00003269366,0.0000238196,0.00006903677,0.0001757253,0.0001570341,0.00001422639,0.0000124796],"category_scores_gemma":[0.000001518085,0.00003233554,0.00002915626,0.000182788,0.000007656382,0.0001056227,0.00005287649,0.00002337559,0.0001109449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001011391,"about_ca_system_score_gemma":0.000007426777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004100568,"about_ca_topic_score_gemma":0.000002208945,"domain_scores_codex":[0.999545,0.00000482006,0.0000813088,0.0002104996,0.00006823944,0.00009016311],"domain_scores_gemma":[0.9996851,0.00005390159,0.00001048528,0.0002083366,0.0000148496,0.00002734542],"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":[6.583997e-7,0.00001648994,0.00001267125,0.00001416877,0.000004042298,6.083234e-7,0.00001203612,0.001156809,0.0006690807,0.7769754,0.1770008,0.04413726],"study_design_scores_gemma":[0.00002718861,0.000006791991,0.0002719814,0.000005558545,0.00000265175,0.000001705514,9.75504e-7,0.6633182,0.0001164241,0.001831031,0.3343778,0.00003972186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00372743,0.00006420701,0.9926667,0.002499875,0.0002607091,0.000189796,0.0001062839,0.0001542738,0.0003307193],"genre_scores_gemma":[0.9707888,0.000005095563,0.02712215,0.0002344013,0.0001510681,0.00007798964,0.0006727185,0.000005724467,0.0009420643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9670613,"threshold_uncertainty_score":0.1694523,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02191931866289084,"score_gpt":0.293850966176401,"score_spread":0.2719316475135102,"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."}}