<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-average-acceptance-length-and-speedup-ratio</loc><lastmod>2026-05-15T09:41:54.282Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-average-acceptance-length-speedup-ratio</loc><lastmod>2026-05-15T09:41:54.253Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-dialogue-on-mt-bench-acceptance-length-and-speedup-ratio</loc><lastmod>2026-05-15T09:41:54.219Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bioacoustic-analysis-on-vocal-repertoire</loc><lastmod>2026-05-15T09:08:28.098Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bioacoustic-identification-on-individual-id</loc><lastmod>2026-05-15T09:08:28.051Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bioacoustic-detection-on-beans-detection</loc><lastmod>2026-05-15T09:08:27.975Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bioacoustic-classification-on-beans</loc><lastmod>2026-05-15T09:08:27.932Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-pst900-50-percent</loc><lastmod>2026-05-15T08:53:48.680Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-semanticrt-5-percent</loc><lastmod>2026-05-15T08:53:48.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-to-online-reinforcement-learning-on-d4rl-antmaze-all-configurations</loc><lastmod>2026-05-15T08:34:35.946Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-image-detection-on-wildrf</loc><lastmod>2026-07-08T07:51:31.757Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-lrs-vqa</loc><lastmod>2026-05-15T08:27:02.825Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/remote-sensing-image-understanding-on-xlrs-bench</loc><lastmod>2026-05-15T08:27:02.790Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/remote-sensing-image-understanding-on-rshr-bench</loc><lastmod>2026-05-15T08:27:02.760Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-bioasq-test</loc><lastmod>2026-05-15T08:26:52.137Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vector-quantization-on-contriever1m-d-768-test</loc><lastmod>2026-05-15T08:10:53.177Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vector-quantization-on-fb-ssnpp1m-d-256-test</loc><lastmod>2026-05-15T08:10:53.146Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-and-question-answering-on-arc-e-arc-c-winogrande-boolq-piqa-hellaswag-obqa-hqa</loc><lastmod>2026-05-15T06:36:13.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-cosmosqa-test</loc><lastmod>2026-05-15T06:26:11.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/class-incremental-learning-on-food</loc><lastmod>2026-05-14T10:10:40.553Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/class-incremental-learning-on-sun</loc><lastmod>2026-05-14T10:10:40.524Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/class-incremental-learning-on-ucf</loc><lastmod>2026-05-14T10:10:40.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/class-incremental-learning-on-cars-average-and-last-accuracy</loc><lastmod>2026-05-14T10:10:40.467Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binding-affinity-regression-on-misato-structure-split</loc><lastmod>2026-05-14T09:59:04.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/enzyme-commission-depth-1-function-prediction-on-misato-structure</loc><lastmod>2026-05-14T09:59:03.935Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fair-clustering-on-synthetic-a</loc><lastmod>2026-05-14T09:56:03.899Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fair-clustering-on-synthetic-b</loc><lastmod>2026-05-14T09:56:03.831Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-path-finding-on-large-maze-33x33-world-size-33-0-percent-static-obstacle-rate</loc><lastmod>2026-05-14T09:06:55.313Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-path-finding-on-medium-warehouse-25x25-34-6-percent-static-obstacles</loc><lastmod>2026-05-14T09:06:55.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-path-finding-on-medium-room-23x23-world-size-33-5-percent-static-obstacle-rate</loc><lastmod>2026-05-14T09:06:55.255Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-path-finding-on-medium-maze-25x25-32-8-percent-static-obstacles</loc><lastmod>2026-05-14T09:06:55.228Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-path-finding-on-small-random-10x10-world-size-17-5-percent-static-obstacle-rate</loc><lastmod>2026-05-14T09:06:55.195Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-shape-registration-on-dt4d-h-test</loc><lastmod>2026-05-14T08:28:00.491Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-shape-registration-on-shrec07-h-test</loc><lastmod>2026-05-14T08:28:00.462Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-hallusionbench</loc><lastmod>2026-06-01T07:33:47.584Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-fusionbench-20-task-suite</loc><lastmod>2026-05-14T08:06:45.341Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-fusionbench-14-task-suite</loc><lastmod>2026-05-14T08:06:45.310Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/centerline-tracking-on-barcelona-catalunya-gp-circuit</loc><lastmod>2026-05-14T07:58:09.690Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-multi-class-classification-on-hardcop-38-datasets-original</loc><lastmod>2026-05-14T07:49:29.353Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-traffic-5-percent-train-test</loc><lastmod>2026-05-14T07:25:49.518Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-electricity-5-percent-train-data-test</loc><lastmod>2026-05-14T07:25:49.450Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-ettm1-5-percent-train-test</loc><lastmod>2026-05-14T07:25:49.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-etth1-5-percent-training-data-test</loc><lastmod>2026-05-14T07:25:49.278Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-ettm1-10-percent-train</loc><lastmod>2026-05-14T07:25:49.037Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-understanding-and-reasoning-on-llm-downstream-evaluation-suite-subset-arc-c-boolq-winogrande-gsm8k-mmlu-zero-shot</loc><lastmod>2026-05-14T07:15:11.118Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-mcqa-on-mmlu-16-subjects-filtered</loc><lastmod>2026-05-14T07:15:12.825Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-reasoning-on-toolalpaca</loc><lastmod>2026-05-26T11:06:27.547Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/top-k-selection-on-array-of-262-144-elements-top-1024-selection-test</loc><lastmod>2026-05-14T06:44:57.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empirical-coverage-estimation-on-riverswim-t-50-90-percent-coverage</loc><lastmod>2026-05-13T11:15:42.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-policy-recovery-empirical-coverage-on-riverswim-t-50-nominal-95-percent-coverage</loc><lastmod>2026-05-13T11:15:41.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/state-value-coverage-estimation-on-riverswim-mostly-right-policy-t-50</loc><lastmod>2026-05-13T11:15:41.832Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-value-coverage-estimation-on-riverswim-mostly-right-target-policy-t-50</loc><lastmod>2026-05-13T11:15:41.806Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empirical-coverage-estimation-on-riverswim-t-10-95-percent-coverage</loc><lastmod>2026-05-13T11:15:41.782Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/off-policy-evaluation-on-riverswim-mostly-left-policy-t-50</loc><lastmod>2026-05-13T11:15:41.581Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/state-value-estimation-coverage-on-riverswim</loc><lastmod>2026-05-13T11:15:41.543Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/state-action-value-estimation-coverage-on-riverswim</loc><lastmod>2026-05-13T11:15:41.507Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-geneval-553-prompts-4-samples-each-full</loc><lastmod>2026-06-24T07:47:34.120Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/allocation-problem-optimization-on-monte-carlo-simulated-allocation-datasets</loc><lastmod>2026-05-13T10:47:56.963Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-conflictkg</loc><lastmod>2026-05-13T10:44:36.113Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-counterfacts-accuracy</loc><lastmod>2026-05-13T10:44:36.073Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/transition-prediction-on-cascadebench</loc><lastmod>2026-05-13T10:44:35.635Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-prediction-on-trentino-internet</loc><lastmod>2026-05-15T07:13:48.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-test-accuracy-percent</loc><lastmod>2026-05-13T09:27:34.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-test-accuracy-percent</loc><lastmod>2026-05-13T09:27:34.216Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-preference-optimization-on-helpsteer2</loc><lastmod>2026-05-13T09:15:56.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-preference-optimization-on-ultrafeedback</loc><lastmod>2026-05-13T09:15:56.683Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-minervamath-held-out</loc><lastmod>2026-05-13T09:04:04.289Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt-2025-held-out</loc><lastmod>2026-05-13T09:04:04.251Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2026-held-out</loc><lastmod>2026-05-13T09:04:04.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-grounding-on-video-sal2</loc><lastmod>2026-05-13T09:04:03.640Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-understanding-on-omnivid</loc><lastmod>2026-05-13T09:04:03.600Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-understanding-on-video-mme-video-mme-avg-percent</loc><lastmod>2026-05-13T09:04:03.558Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-understanding-on-daily-omni</loc><lastmod>2026-05-13T09:04:03.517Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-distribution-modeling-on-rotated-grid</loc><lastmod>2026-05-13T08:45:40.714Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-distribution-modeling-on-branched-manifold</loc><lastmod>2026-05-13T08:45:40.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/workflow-steering-attack-on-misinfotask-108-constrained-analytical-tasks</loc><lastmod>2026-05-13T08:43:58.468Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-skeleton-based-action-recognition-on-ntu-rgb-plus-d-xsub-120-96-24</loc><lastmod>2026-05-13T08:37:06.019Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-skeleton-based-action-recognition-on-ntu-rgb-plus-d-xsub-60-48-12</loc><lastmod>2026-05-13T08:37:05.941Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/system-identification-on-heat-exchanger</loc><lastmod>2026-05-13T08:26:00.662Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/system-identification-on-mr-damper</loc><lastmod>2026-05-13T08:26:00.634Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/system-identification-on-hair-dryer</loc><lastmod>2026-05-13T08:26:00.600Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/system-identification-on-robot-arm</loc><lastmod>2026-05-13T08:26:00.573Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-recognition-on-breakfast-actions-train-test</loc><lastmod>2026-05-13T08:03:44.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-conll04</loc><lastmod>2026-05-13T07:53:43.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-dfdc</loc><lastmod>2026-05-13T07:45:35.444Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-celeb-df</loc><lastmod>2026-05-13T07:45:35.397Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-unseen-generators-average</loc><lastmod>2026-05-13T07:45:35.363Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-flux-unseen</loc><lastmod>2026-05-13T07:45:35.325Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-float-unseen</loc><lastmod>2026-05-13T07:45:35.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-real3dportrait-unseen</loc><lastmod>2026-05-13T07:45:35.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-anitalker-unseen</loc><lastmod>2026-05-13T07:45:35.235Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-edtalk-unseen</loc><lastmod>2026-05-13T07:45:35.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-diffusionact-unseen</loc><lastmod>2026-05-13T07:45:35.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-fsrt-unseen</loc><lastmod>2026-05-13T07:45:35.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-lia-unseen</loc><lastmod>2026-05-13T07:45:35.098Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-attribution-on-liveportrait-unseen</loc><lastmod>2026-05-13T07:45:35.062Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-preference-alignment-on-mt-bench</loc><lastmod>2026-06-09T10:19:14.851Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gender-classification-on-coco-100-percent-spurious-correlation</loc><lastmod>2026-05-13T07:23:32.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-security-evaluation-on-agentdojo-v1-97-benign-tasks-27-injection-tasks</loc><lastmod>2026-05-13T07:14:09.908Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-document-reasoning-on-vdr</loc><lastmod>2026-05-12T16:52:01.641Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-evaluation-on-chair-test</loc><lastmod>2026-05-12T16:28:47.170Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-segmentation-on-trashcan</loc><lastmod>2026-05-12T16:14:08.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-view-interpolation-on-dynamic-object-dataset</loc><lastmod>2026-05-12T16:57:34.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/contextual-integrity-reasoning-on-privacylens</loc><lastmod>2026-05-12T16:07:03.082Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/formula-translation-complexity-analysis-on-temporal-logic-requirement-patterns-past-semantics</loc><lastmod>2026-05-12T15:45:20.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mtl-formula-complexity-analysis-on-fretish-requirement-patterns-finite-semantics</loc><lastmod>2026-05-12T15:45:20.219Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dense-image-generation-on-unifybench-plus-plus</loc><lastmod>2026-05-12T15:44:19.609Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-pcam-task-utility-percent</loc><lastmod>2026-05-12T15:12:46.978Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mhist-task-utility-percent</loc><lastmod>2026-05-12T15:12:46.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-crc100k</loc><lastmod>2026-05-12T15:12:46.903Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/report-generation-on-mimic-factual-consistency-and-completeness</loc><lastmod>2026-05-12T15:12:46.869Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/report-generation-on-iu-xray-factual-consistency-completeness</loc><lastmod>2026-05-12T15:12:46.838Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-mimic</loc><lastmod>2026-05-12T15:12:46.810Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-iu-xray</loc><lastmod>2026-05-12T15:12:46.775Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/true-false-question-answering-on-mimic</loc><lastmod>2026-05-12T15:12:46.737Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/true-false-question-answering-on-iu-xray</loc><lastmod>2026-05-12T15:12:46.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-vocabulary-detection-on-lvis-ov-val</loc><lastmod>2026-05-12T14:56:23.039Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-environment-decision-making-on-crafter-balrog-protocol</loc><lastmod>2026-07-02T09:33:25.225Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interaction-type-prediction-on-shs148k-bfs</loc><lastmod>2026-05-12T14:03:19.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interaction-type-prediction-on-shs148k-dfs</loc><lastmod>2026-05-12T14:03:19.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interaction-type-prediction-on-shs148k-random</loc><lastmod>2026-05-12T14:03:19.563Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interaction-type-prediction-on-shs27k-bfs</loc><lastmod>2026-05-12T14:03:19.526Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interaction-type-prediction-on-shs27k-dfs</loc><lastmod>2026-05-12T14:03:19.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interaction-type-prediction-on-shs27k-random</loc><lastmod>2026-05-12T14:03:19.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toxicity-detection-on-civilcomments-bert-test</loc><lastmod>2026-05-12T13:48:40.307Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/calibration-on-celeba-imageresnet-test</loc><lastmod>2026-05-12T13:48:39.785Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-evaluation-on-aggregated-downstream-suite-math_500-gsm8k-ifeval-arc-hellaswag-mmlu-mbpp-plus-humaneval-plus-wildguard-harmbench</loc><lastmod>2026-05-12T13:32:14.584Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/assistant-response-generation-on-wildbench-v2</loc><lastmod>2026-05-12T13:02:17.840Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-time-series-anomaly-detection-on-swat-auc-roc-auc-pr-vus-roc-vus-pr</loc><lastmod>2026-06-05T08:09:36.955Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ms-lesion-segmentation-on-mslesseg</loc><lastmod>2026-05-12T12:52:01.236Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ms-lesion-segmentation-on-msseg-1</loc><lastmod>2026-05-12T12:52:01.187Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-and-reasoning-on-mmlu-pro</loc><lastmod>2026-05-12T12:34:32.367Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-tuning-on-tydiqa</loc><lastmod>2026-05-12T12:01:46.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-reasoning-on-locomo</loc><lastmod>2026-05-12T11:46:56.067Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-reasoning-on-scienceworld</loc><lastmod>2026-05-12T11:46:56.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-reasoning-on-alfworld-detailed-metrics</loc><lastmod>2026-05-12T11:46:56.010Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lifestyle-classification-on-longitudinal-wearable-sensor-waveforms</loc><lastmod>2026-05-12T11:23:38.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-25-m-decoder</loc><lastmod>2026-05-12T11:17:35.648Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memorization-detection-on-aime-math500-perturbed-distribution</loc><lastmod>2026-05-12T11:01:25.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memorization-detection-on-aime-math500-translated-distribution</loc><lastmod>2026-05-12T11:01:25.091Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memorization-detection-on-aime-math500-rephrased-distribution</loc><lastmod>2026-05-12T11:01:25.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memorization-detection-on-aime-math500-original-distribution</loc><lastmod>2026-05-12T11:01:25.013Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-reasoning-on-androidworld</loc><lastmod>2026-05-12T10:25:33.266Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rollout-forecasting-on-bve-30-trajectory-test</loc><lastmod>2026-05-12T10:01:04.409Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/micro-video-recommendation-on-microlens-100k-test</loc><lastmod>2026-05-12T09:51:41.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decoding-on-rtx-6000-ada-platform</loc><lastmod>2026-05-12T09:40:57.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decoding-performance-on-rtx-4090-platform</loc><lastmod>2026-05-12T09:40:57.491Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decoding-on-dgx-a100-platform</loc><lastmod>2026-05-12T09:40:57.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-lighteval-m-leval-test</loc><lastmod>2026-05-12T09:24:21.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-penbased</loc><lastmod>2026-05-12T09:23:19.087Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-anuran-calls</loc><lastmod>2026-05-12T09:23:19.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-phoneme</loc><lastmod>2026-05-12T09:23:18.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-tuandromd</loc><lastmod>2026-05-12T09:23:18.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-rice</loc><lastmod>2026-05-12T09:23:18.879Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-msra25</loc><lastmod>2026-05-12T09:23:18.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-mice-protein-ari-ami</loc><lastmod>2026-05-12T09:23:18.724Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-pima</loc><lastmod>2026-05-12T09:23:18.687Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-seeds-ari-ami</loc><lastmod>2026-05-12T09:23:18.652Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-all-average</loc><lastmod>2026-05-12T09:11:47.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amo-bench-acc-tok</loc><lastmod>2026-05-12T09:11:47.850Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-accuracy-and-token-count</loc><lastmod>2026-05-12T09:11:47.816Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-acc-tok</loc><lastmod>2026-05-12T09:11:47.784Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-acc-tok</loc><lastmod>2026-05-12T09:11:47.746Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/harmful-prompt-detection-on-xstest</loc><lastmod>2026-06-02T11:43:40.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-step-reasoning-on-strategyqa</loc><lastmod>2026-07-08T06:40:38.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/puzzle-reasoning-on-reasoning-gym-test</loc><lastmod>2026-05-12T08:30:38.499Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-v6-test-avg-at-4</loc><lastmod>2026-05-12T08:30:38.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-livemathbench-v202505-test</loc><lastmod>2026-05-12T08:30:38.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-objective-retrieval-on-needlebench-m-rt-32k-context-stress-slice</loc><lastmod>2026-05-12T07:21:39.842Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnostic-classification-on-ham-and-melanoma-joint</loc><lastmod>2026-05-12T07:20:15.867Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnostic-classification-on-melanoma-zero-shot-1000</loc><lastmod>2026-05-12T07:20:15.771Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-etth2-mse-and-relative-improvement</loc><lastmod>2026-06-02T12:53:34.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-manipulation-on-metaworld-mt50</loc><lastmod>2026-05-11T10:39:54.331Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-swat-cross-domain-val</loc><lastmod>2026-05-11T10:30:51.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-aramis</loc><lastmod>2026-05-11T10:30:51.884Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ood-detection-on-ood-datasets-mean</loc><lastmod>2026-05-11T10:29:50.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/full-spectrum-out-of-distribution-detection-on-texture-test</loc><lastmod>2026-05-11T10:29:50.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/full-spectrum-out-of-distribution-detection-on-ssb-hard-test</loc><lastmod>2026-05-11T10:29:50.557Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-avg-at-1-8-e_m-pass-at-1-8-e_m</loc><lastmod>2026-05-14T07:00:31.426Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/worst-case-angular-error-estimation-on-1-million-randomly-generated-unit-vectors</loc><lastmod>2026-05-11T10:02:04.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-incremental-learning-on-mtil-few-shot-order-ii-test</loc><lastmod>2026-05-11T09:39:34.516Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-generation-with-gender-alignment-on-ffhq</loc><lastmod>2026-05-11T09:31:14.095Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-generation-on-caltech-256</loc><lastmod>2026-05-11T09:25:10.352Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-vqa-test-using-bs-and-meteor</loc><lastmod>2026-05-11T09:25:10.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-mmlu-test</loc><lastmod>2026-05-11T09:25:10.250Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-fashion-mnist-accuracy</loc><lastmod>2026-07-09T06:36:39.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bike-localization-on-customized-dataset-seen</loc><lastmod>2026-05-11T09:13:30.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-efficiency-and-early-exit-metrics</loc><lastmod>2026-05-11T08:57:47.993Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-100-exit-layer-efficiency-and-accuracy</loc><lastmod>2026-05-11T08:57:47.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-latency-and-efficiency-profile</loc><lastmod>2026-05-11T08:57:47.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-100-l-bops-accuracy</loc><lastmod>2026-05-11T08:57:47.817Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-speedup-average-accepted-length-drafting-cost</loc><lastmod>2026-05-11T08:44:39.656Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-gdelt-emerging</loc><lastmod>2026-05-11T08:19:52.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-icews05-15-emerging</loc><lastmod>2026-05-11T08:19:52.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-icews-18-emerging</loc><lastmod>2026-05-11T08:19:52.002Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-icews14-emerging</loc><lastmod>2026-05-11T08:19:51.973Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-diagnosis-on-agentclinic-ood-original-test</loc><lastmod>2026-05-11T08:06:14.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-google-reviews</loc><lastmod>2026-05-11T07:54:08.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-reversal-sensitivity-analysis-on-diabetes-experiment-conditional-outcome-distributions-mu</loc><lastmod>2026-05-11T06:38:38.932Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fixed-response-on-fixed-response</loc><lastmod>2026-05-08T11:41:21.471Z</lastmod></url></urlset>