{"id":"W4413438078","doi":"10.62051/m633as12","title":"Towards Efficient LLMs: Analyzing Computational Bottlenecks and Optimization Strategies","year":2025,"lang":"en","type":"article","venue":"Transactions on Computer Science and Intelligent Systems Research","topic":"Scheduling and Optimization Algorithms","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Arts Foundation; University of Toronto","funders":"","keywords":"Computer science","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":[0.007196169,0.001403641,0.001762762,0.002290616,0.001011756,0.004483421,0.003105491,0.00166305,0.008518218],"category_scores_gemma":[0.0396645,0.0009581184,0.00109662,0.002181113,0.001529127,0.01088598,0.001941485,0.003121069,0.001638753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003022087,"about_ca_system_score_gemma":0.005615623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005978185,"about_ca_topic_score_gemma":0.005495049,"domain_scores_codex":[0.9961124,0.001929416,0.0002087223,0.0005946986,0.00065732,0.0004973835],"domain_scores_gemma":[0.9802082,0.01470495,0.0009986561,0.001834915,0.001687375,0.0005659743],"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":[0.0005981835,0.0006723449,0.006099608,0.001031208,0.0001845543,0.0001488172,0.0006194704,0.612928,0.005689256,0.1510013,0.0106128,0.2104144],"study_design_scores_gemma":[0.00002089393,0.00005778295,0.000232721,0.0000250848,0.00002025544,0.00002629556,0.000136976,0.9563128,0.001168849,0.04084491,0.001139599,0.00001377578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07488589,0.002090658,0.9092343,0.002595289,0.0001367212,0.0003149428,0.000279357,0.001846121,0.008616633],"genre_scores_gemma":[0.5625178,0.001381691,0.4293711,0.0004992586,0.0001640316,0.0004937283,0.0006029889,0.0008599633,0.004109411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008518218,"threshold_uncertainty_score":0.03805745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03569556815364451,"score_gpt":0.3257574598475096,"score_spread":0.2900618916938651,"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."}}