{"id":"W4417285899","doi":"10.1109/iccv51701.2025.01969","title":"VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","year":2025,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"ENCODE; Security token; Encoding (memory); Benchmark (surveying); Reduction (mathematics); Quadratic equation; Video tracking; Minification","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":[0.0001755641,0.0001431456,0.0001309016,0.0001813955,0.0002681771,0.0001808155,0.0005772618,0.00002833322,0.00003882406],"category_scores_gemma":[0.00001532325,0.0001153671,0.00004540708,0.0006284519,0.00005527959,0.0003103392,0.00009207311,0.0002067891,0.00005185089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001572022,"about_ca_system_score_gemma":0.0001088357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004315919,"about_ca_topic_score_gemma":0.0001016625,"domain_scores_codex":[0.9989082,0.00003421812,0.0001621226,0.0004036025,0.0002059342,0.0002859611],"domain_scores_gemma":[0.999256,0.0001383589,0.00004141686,0.0004465051,0.00003668161,0.00008110475],"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":[0.00001802779,0.00009572883,0.03010815,0.00005367303,0.00009992698,0.00002453725,0.0002869421,0.002661584,0.0005165699,0.919165,0.002270323,0.04469958],"study_design_scores_gemma":[0.002967649,0.0002797119,0.1295206,0.0002797642,0.00009106703,0.0001040557,0.0004823112,0.804541,0.01002505,0.04233921,0.008107667,0.001261979],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01361009,0.0000173067,0.9165506,0.007115223,0.00006857628,0.0002441757,0.000001073525,0.0004597967,0.06193316],"genre_scores_gemma":[0.9528431,0.000003448531,0.04502717,0.0007737202,0.00001293433,0.00003684906,0.000002894904,0.000008993245,0.001290949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9392329,"threshold_uncertainty_score":0.4704536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396152452388519,"score_gpt":0.2584024205232704,"score_spread":0.2444408959993853,"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."}}