{"id":"W4416284722","doi":"10.1109/iccv51701.2025.00277","title":"Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration","keywords":"Overfitting; Security token; Scalability; Adaptability; Task (project management); Adaptation (eye); Limit (mathematics); Gradient descent; Artificial neural network","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":[0.0006564076,0.0002276252,0.0002342939,0.0003058088,0.0004972703,0.0003314766,0.000464432,0.000104974,0.00002978923],"category_scores_gemma":[0.0002056496,0.0002259929,0.0001498646,0.0005645457,0.00004058841,0.0004972392,0.00004650835,0.0002626905,0.00003118366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001272489,"about_ca_system_score_gemma":0.0001078594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001165312,"about_ca_topic_score_gemma":0.0001175037,"domain_scores_codex":[0.9981951,0.0001254004,0.0003707332,0.0005498322,0.0002823505,0.0004765903],"domain_scores_gemma":[0.9988343,0.0003953704,0.0001326597,0.0003429963,0.0001679182,0.000126724],"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":[0.0002176386,0.0003455066,0.00529026,0.0004314309,0.0001441153,0.00001597345,0.01124084,0.3211487,0.01654788,0.5215772,0.002888298,0.1201521],"study_design_scores_gemma":[0.001515103,0.00009318517,0.002512789,0.00006440381,0.00001202806,0.000001166964,0.0004027126,0.7570451,0.002119607,0.0001655494,0.2358448,0.0002235412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002273797,0.0001745686,0.9767367,0.00496074,0.0003806085,0.0006305361,0.000001249998,0.00049219,0.01434961],"genre_scores_gemma":[0.7377429,0.00002106446,0.2462179,0.00128966,0.00003796152,0.00008298895,0.00002339221,0.00002196858,0.01456218],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7354691,"threshold_uncertainty_score":0.9215721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03317788782132405,"score_gpt":0.2888005095702287,"score_spread":0.2556226217489047,"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."}}