{"id":"W7117709618","doi":"10.18280/isi.301112","title":"Efficient Transformer Architectures via Learnable Sparse Attention and Optimization","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Digital Filter Design and Implementation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Transformer; Minification; Optimization problem; Constrained optimization; Optimization algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006470075,0.0003828977,0.0003239433,0.0008707908,0.0006794605,0.002059532,0.0003632172,0.000168536,0.00005644828],"category_scores_gemma":[0.00009665342,0.0003965106,0.0001218767,0.001197635,0.0002360524,0.003134929,0.0001216506,0.0002032277,0.00005990145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003230285,"about_ca_system_score_gemma":0.0001922506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001089321,"about_ca_topic_score_gemma":0.00000805996,"domain_scores_codex":[0.9972987,0.000141948,0.001170631,0.0003630785,0.0004607502,0.0005649409],"domain_scores_gemma":[0.9986508,0.00006954559,0.0004050077,0.0003638995,0.0003723745,0.0001383472],"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":[0.00008474381,0.00007097523,0.000315228,0.0008004519,0.0000820002,0.000001264906,0.006864041,0.3180837,0.0004148874,0.008439945,0.0002205,0.6646222],"study_design_scores_gemma":[0.001145434,0.0002452105,0.004594855,0.0004907703,0.00006745134,0.00003641149,0.0005356576,0.9859005,0.001375885,0.003977553,0.001228326,0.0004019958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05007802,0.0002902023,0.9324535,0.0002926843,0.0008417565,0.00102498,0.00002432099,0.0001571186,0.01483742],"genre_scores_gemma":[0.9798981,0.00007760627,0.01885685,0.0004811395,0.00003785363,0.00006650689,0.0001273547,0.00001274551,0.0004418734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9298201,"threshold_uncertainty_score":0.9998487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01315322231391874,"score_gpt":0.2374645899890035,"score_spread":0.2243113676750847,"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."}}