{"id":"W7139957846","doi":"10.1109/hipc66333.2025.00027","title":"IMBPS - Iterative MLP Blocks with Parameter Splits for Improving LLM Inference","year":2025,"lang":"","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Pattern recognition (psychology); Iterative method; Inference; Noise (video); Feature (linguistics)","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":[0.001403627,0.001121093,0.0006198803,0.0004781733,0.0004026261,0.0009259285,0.002109096,0.0008012349,0.005759591],"category_scores_gemma":[0.005813176,0.0005783739,0.0005595888,0.0005301625,0.0006355383,0.002801382,0.001765922,0.001650473,0.003326194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008074382,"about_ca_system_score_gemma":0.002180978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00540468,"about_ca_topic_score_gemma":0.01028908,"domain_scores_codex":[0.9993547,0.000223013,0.00004211384,0.0001035591,0.0001845943,0.00009207082],"domain_scores_gemma":[0.9985123,0.0006914847,0.0001083608,0.0003960724,0.0002214234,0.00007033053],"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":[0.0007429144,0.0003278711,0.002787699,0.0002145201,0.000132329,0.0001842552,0.0003382615,0.3293441,0.04823203,0.02195353,0.009909323,0.5858332],"study_design_scores_gemma":[0.00001997896,0.00004816177,0.0001688614,0.000008061206,0.00001152004,0.00002377845,0.00002100704,0.9805963,0.01251537,0.005219686,0.001360743,0.000006562852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03059153,0.000255348,0.959453,0.0002618503,0.00003611665,0.00007182277,0.0001485072,0.00663182,0.002550043],"genre_scores_gemma":[0.3363639,0.0001792827,0.6569142,0.000281708,0.00005174734,0.0002463516,0.0007695341,0.0006958398,0.004497474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005759591,"threshold_uncertainty_score":0.0192678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01280708646338322,"score_gpt":0.2969934484502292,"score_spread":0.284186361986846,"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."}}