<?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/caption-hallucination-analysis-on-coco</loc><lastmod>2026-06-09T06:53:44.751Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hierarchical-time-series-forecasting-on-australian-tourism-test</loc><lastmod>2026-06-04T11:24:54.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traveling-salesman-problem-on-synthetic-tsp1k</loc><lastmod>2026-06-04T10:51:01.134Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-generation-on-hydrocarbon-chains</loc><lastmod>2026-06-04T10:42:25.994Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-generation-on-acrylates-acry</loc><lastmod>2026-06-04T10:42:25.964Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cs-mri-reconstruction-on-brain-test</loc><lastmod>2026-06-04T09:46:24.264Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meme-generation-on-goat-g-test</loc><lastmod>2026-06-04T09:42:51.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meme-generation-on-muse-test</loc><lastmod>2026-06-04T09:42:51.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meme-generation-on-met-meme-test</loc><lastmod>2026-06-04T09:42:51.894Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meme-generation-on-memecap-test</loc><lastmod>2026-06-04T09:42:51.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meme-generation-on-memereacon-pi-g-test</loc><lastmod>2026-06-04T09:42:51.833Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meme-generation-on-memereacon-pc-g-test</loc><lastmod>2026-06-04T09:42:51.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/random-image-inpainting-on-ffhq-256-x-256</loc><lastmod>2026-06-30T07:27:06.886Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-tabular-data-generation-on-90-mcar-scenarios-6-datasets-x-5-missing-ratios</loc><lastmod>2026-06-04T08:54:52.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-generation-on-mar-benchmark-90-scenarios-aggregated</loc><lastmod>2026-06-04T08:54:52.962Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-inference-on-jobs-real-world-evaluation</loc><lastmod>2026-06-04T08:50:21.067Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-ogbn-arxiv-3-shot</loc><lastmod>2026-06-11T10:09:06.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-pubmed-3-shot</loc><lastmod>2026-06-11T10:09:06.693Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-citeseer-3-shot</loc><lastmod>2026-06-11T10:09:06.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-force-and-energy-prediction-on-rmd17</loc><lastmod>2026-06-04T08:35:39.241Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-force-and-energy-prediction-r-2-on-md17</loc><lastmod>2026-06-04T08:35:39.213Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/force-prediction-on-rmd17</loc><lastmod>2026-06-16T09:00:17.517Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyperspectral-reconstruction-on-ntire-hyper-skin-target-2022-train</loc><lastmod>2026-06-04T07:48:26.277Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyperspectral-reconstruction-on-ntire-hyper-skin-target-2020-train</loc><lastmod>2026-06-04T07:48:26.247Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/through-plane-super-resolution-on-uk-biobank-flair</loc><lastmod>2026-06-04T07:28:20.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/survival-on-synthetic</loc><lastmod>2026-06-04T07:08:14.220Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ranking-on-synthetic</loc><lastmod>2026-06-04T07:08:14.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-synthetic-excess-test-loss</loc><lastmod>2026-06-04T07:08:14.163Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-synthetic-median-excess-test-loss-median-selected-iteration</loc><lastmod>2026-06-04T07:08:14.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-video-understanding-on-perceptiontest-perctest</loc><lastmod>2026-06-02T13:52:47.506Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-video-understanding-on-next-qa</loc><lastmod>2026-06-02T13:52:47.473Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-video-understanding-on-longvideobench-lvb</loc><lastmod>2026-06-02T13:52:47.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/state-estimation-on-pendulum</loc><lastmod>2026-06-02T13:07:43.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-geneval-geneval-metric-only</loc><lastmod>2026-06-11T09:20:57.373Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-web-agent-navigation-on-deepshop</loc><lastmod>2026-06-02T12:39:22.710Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/circuit-localization-on-mcqa</loc><lastmod>2026-06-02T11:47:44.841Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-fev-bench-test</loc><lastmod>2026-06-02T11:47:13.811Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-inversion-defense-on-facescrub-224x224-test</loc><lastmod>2026-06-02T11:38:37.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-unigenbench-600-prompts-test</loc><lastmod>2026-06-02T11:27:03.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-protein-grp-percent-mse-95-percent-ci</loc><lastmod>2026-06-02T10:59:00.044Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-metro</loc><lastmod>2026-06-02T10:58:59.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-hepc</loc><lastmod>2026-06-02T10:58:59.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-abalone-grp-percent-mse-95-percent-ci</loc><lastmod>2026-06-02T10:58:59.901Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-refusal-evaluation-on-polyrefuse-yo-1-0</loc><lastmod>2026-06-02T10:38:11.561Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-refusal-evaluation-on-polyrefuse-1-0-si</loc><lastmod>2026-06-02T10:38:11.527Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-refusal-evaluation-on-polyrefuse-1-0-km</loc><lastmod>2026-06-02T10:38:11.486Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-refusal-evaluation-on-polyrefuse-1-0-my</loc><lastmod>2026-06-02T10:38:11.448Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-refusal-evaluation-on-polyrefuse-am-1-0</loc><lastmod>2026-06-02T10:38:11.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-refusal-evaluation-on-polyrefuse-1-0-sw</loc><lastmod>2026-06-02T10:38:11.380Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-kk-all</loc><lastmod>2026-06-02T10:26:41.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-kk-6-8-ppl</loc><lastmod>2026-06-02T10:26:41.668Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-kk-4-5-ppl</loc><lastmod>2026-06-02T10:26:41.626Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-kk-2-3-ppl</loc><lastmod>2026-06-02T10:26:41.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-squad-2-test</loc><lastmod>2026-06-02T10:18:26.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/refusal-on-musique-un</loc><lastmod>2026-06-02T08:56:07.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/faithfulness-evaluation-on-confiqa</loc><lastmod>2026-06-02T08:56:07.485Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-reasoning-on-tat-qa</loc><lastmod>2026-06-02T08:56:07.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/common-sense-reasoning-on-bbh-sports-understanding</loc><lastmod>2026-06-02T10:10:53.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-pass-at-1</loc><lastmod>2026-06-02T07:05:27.037Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-avg-at-16-pass-at-16</loc><lastmod>2026-06-02T07:05:26.997Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-26-avg-at-16-pass-at-16</loc><lastmod>2026-06-02T07:05:26.962Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-video-understanding-on-ovobench-real-time</loc><lastmod>2026-06-01T10:36:15.690Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-wisconsin-breast-cancer</loc><lastmod>2026-07-07T08:33:14.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-video-understanding-on-videomme-overall-w-o-sub-2025</loc><lastmod>2026-06-01T09:14:48.917Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/remaining-useful-life-estimation-on-c-mapss-fd004-test</loc><lastmod>2026-06-01T08:54:42.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/remaining-useful-life-estimation-on-c-mapss-fd003-test</loc><lastmod>2026-06-01T08:54:42.893Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-search-augmented-question-answering-on-popqa</loc><lastmod>2026-06-11T08:47:28.800Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-search-augmented-question-answering-on-triviaqa</loc><lastmod>2026-06-11T08:47:28.718Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-search-augmented-question-answering-on-nq-success-rate-percent</loc><lastmod>2026-06-11T08:47:28.658Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/metric-depth-estimation-on-eth3d-delta1</loc><lastmod>2026-06-01T07:34:17.259Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-squad-f1-and-time</loc><lastmod>2026-06-01T07:34:16.358Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-mmlu-accuracy-and-inference-time</loc><lastmod>2026-06-01T07:34:16.322Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-reasoning-on-all-angles-bench</loc><lastmod>2026-05-29T11:34:34.425Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-execution-on-live-code-execution</loc><lastmod>2026-05-29T10:44:45.540Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-live-code-generation</loc><lastmod>2026-05-29T10:44:45.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-similarity-accuracy-on-sick</loc><lastmod>2026-05-29T10:43:44.309Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-knowledge-editing-on-fgvedit</loc><lastmod>2026-05-29T10:14:18.196Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-gqa-accuracy-and-average-performance-percent</loc><lastmod>2026-07-02T08:33:54.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-cnn-dm-r1-r2-rl-bs-ms-em-cm-sm-ue-fe-fi-sc</loc><lastmod>2026-05-29T08:34:38.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-harmfulness-detection-on-harmbench-suite-harmbench-saferlhf-beavertails-xstest-wildguard</loc><lastmod>2026-05-29T08:33:03.143Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geometric-optimization-on-mmd</loc><lastmod>2026-05-29T08:23:00.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geometric-optimization-on-cp</loc><lastmod>2026-05-29T08:23:00.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-generation-on-llava-bench</loc><lastmod>2026-05-29T08:02:54.169Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-al-gr-released-test</loc><lastmod>2026-05-29T07:33:56.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/abstractive-summarization-on-cnn-dailymail-test</loc><lastmod>2026-06-05T08:23:15.107Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/online-class-incremental-learning-on-imagenet-100-10-tasks-test</loc><lastmod>2026-05-29T07:32:43.093Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-avg-at-12-accuracy</loc><lastmod>2026-05-28T10:34:52.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-avg-at-12-accuracy</loc><lastmod>2026-05-28T10:34:52.576Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-avg-at-12-accuracy</loc><lastmod>2026-05-28T10:34:52.547Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-and-physics-reasoning-on-olympiadbench</loc><lastmod>2026-05-28T09:52:56.805Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-on-naturalplan</loc><lastmod>2026-05-28T09:52:56.764Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-localization-on-visa-auroc-pro-f1-max</loc><lastmod>2026-05-28T09:52:26.174Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-mvtec-ad-auroc-aupr-f1-max</loc><lastmod>2026-05-28T09:52:26.143Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/super-resolution-on-opensarship-test</loc><lastmod>2026-05-28T09:22:35.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-textvqa-vqatext-normalized-average-retention</loc><lastmod>2026-07-07T10:35:12.456Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-manipulation-localization-on-magicbrush</loc><lastmod>2026-06-02T12:58:07.783Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-text-understanding-on-longbench-pro</loc><lastmod>2026-05-28T07:53:59.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/forecasting-on-forecasting-test</loc><lastmod>2026-05-28T07:51:36.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-goal-navigation-on-hm3d-v2</loc><lastmod>2026-06-04T09:31:45.203Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conditional-average-treatment-effect-estimation-on-linear-design-n1-500</loc><lastmod>2026-05-28T07:21:25.884Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-ujiindoorloc</loc><lastmod>2026-05-27T10:13:01.004Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-slice-localization</loc><lastmod>2026-05-27T10:13:00.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-tutoring-on-openlearnlm-ood</loc><lastmod>2026-05-27T10:01:05.636Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-tutoring-on-bigmath-in-domain</loc><lastmod>2026-05-27T10:01:05.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/exposure-correction-on-msec-average-1-test</loc><lastmod>2026-05-27T09:03:16.300Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-disease-diagnosis-on-rsna-ood</loc><lastmod>2026-05-27T09:00:45.937Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-disease-diagnosis-on-nih-google-ood</loc><lastmod>2026-05-27T09:00:45.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-disease-diagnosis-on-vindr-cxr-ood</loc><lastmod>2026-05-27T09:00:45.876Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-disease-diagnosis-on-chestx-ray14-ood</loc><lastmod>2026-05-27T09:00:45.849Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-disease-diagnosis-on-mimic-cxr</loc><lastmod>2026-05-27T09:00:45.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-disease-diagnosis-on-chexpert-test</loc><lastmod>2026-05-27T09:00:45.782Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-navigation-on-eb-navigation</loc><lastmod>2026-07-02T08:22:19.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-restoration-on-i2p-successful-generations</loc><lastmod>2026-05-27T08:00:58.973Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-restoration-on-i2p-all-prompts</loc><lastmod>2026-05-27T08:00:58.928Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-on-i2p</loc><lastmod>2026-05-27T08:00:58.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-visual-question-answering-on-docvqa-score</loc><lastmod>2026-06-19T08:31:19.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/complex-query-answering-k-2-free-variables-on-fb15k-237</loc><lastmod>2026-05-26T13:29:48.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-to-video-reconstruction-on-event-to-video-datasets-test</loc><lastmod>2026-05-26T12:42:50.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-utility-on-mmmu</loc><lastmod>2026-05-26T10:59:08.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-utility-on-realworldqa</loc><lastmod>2026-05-26T10:59:08.378Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-hallucination-on-chair</loc><lastmod>2026-05-26T10:59:08.339Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-performance-assessment-on-overall-combined-benchmarks</loc><lastmod>2026-05-26T10:50:47.989Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-knowledge-on-include-lite</loc><lastmod>2026-05-26T10:50:47.952Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-knowledge-on-global-mmlu-lite</loc><lastmod>2026-05-26T10:50:47.907Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-mgsm-v2</loc><lastmod>2026-05-26T10:50:47.871Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-generation-on-care-pro</loc><lastmod>2026-05-26T10:50:47.828Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regional-knowledge-and-conversational-settings-on-care</loc><lastmod>2026-05-26T10:50:47.783Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/camera-control-video-generation-on-single-effect-camera-control-dataset</loc><lastmod>2026-05-26T10:49:05.962Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-accuracy-on-arc-c</loc><lastmod>2026-06-30T06:45:18.553Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conformal-prediction-on-imagenet-five-repeated-splits</loc><lastmod>2026-05-26T09:28:43.499Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/calibration-on-tabular-datasets</loc><lastmod>2026-05-26T08:21:26.509Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-score</loc><lastmod>2026-05-26T08:18:19.807Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-raw-score</loc><lastmod>2026-05-26T08:18:19.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-controllability-on-safety-domains</loc><lastmod>2026-05-26T07:39:53.111Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-rule-chaining-test</loc><lastmod>2026-05-26T07:38:05.725Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constraint-satisfaction-on-graph-coloring-test</loc><lastmod>2026-05-26T07:38:05.688Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constraint-satisfaction-on-n-queens-n-8-test</loc><lastmod>2026-05-26T07:38:05.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-rule-chaining</loc><lastmod>2026-05-26T07:38:05.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/combinatorial-search-on-n-queens-n-8</loc><lastmod>2026-05-26T07:38:05.493Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-minerva-math-4-shot</loc><lastmod>2026-05-26T07:30:18.345Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/software-vulnerability-detection-on-osv-bench-1-0-test</loc><lastmod>2026-05-26T07:17:57.578Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-codecontests-signal-ut-code-bon</loc><lastmod>2026-05-25T08:42:51.528Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-signal-ut-code-bon</loc><lastmod>2026-05-25T08:42:51.493Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livebench-signal-ut-code-bon</loc><lastmod>2026-05-25T08:42:51.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-dimensional-optimization-on-mslr</loc><lastmod>2026-05-25T08:40:20.266Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-generation-on-wan-1-3b-81-frames-832-480-2-1</loc><lastmod>2026-06-26T08:24:44.874Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-path-planning-on-textualized-gridworld-long-targets-test</loc><lastmod>2026-05-25T07:38:37.940Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-path-planning-on-textualized-gridworld-safe-targets-test</loc><lastmod>2026-05-25T07:38:37.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-path-planning-on-textualized-gridworld-short-targets-test</loc><lastmod>2026-05-25T07:38:37.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fair-agent-decision-making-on-school-admission-continuous</loc><lastmod>2026-05-22T08:39:09.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/aspect-based-sentiment-analysis-on-restaurant-14</loc><lastmod>2026-05-22T08:32:35.212Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speaker-independent-keyword-spotting-on-libriphrase-hard</loc><lastmod>2026-05-22T08:18:53.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/specific-adversarial-attack-performance-on-cifar-10</loc><lastmod>2026-05-22T07:05:54.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-content-search-on-synthetic-2048-x-2048-instances</loc><lastmod>2026-05-22T06:55:50.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-accuracy</loc><lastmod>2026-05-21T13:25:42.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-scrna-seq-modeling-under-sparsity-on-dr-drosophila-hard-sparse-modeling</loc><lastmod>2026-05-21T12:25:21.385Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-scrna-seq-extrapolation-on-dr-drosophila-medium-extrapolation</loc><lastmod>2026-05-21T12:25:21.346Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-scrna-seq-interpolation-on-dr-drosophila-easy-interpolation</loc><lastmod>2026-05-21T12:25:21.309Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-trading-on-dow-jones-30-test</loc><lastmod>2026-05-21T12:15:19.758Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-scienceqa-sqa-img</loc><lastmod>2026-06-18T07:46:15.070Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-calibration-metrics</loc><lastmod>2026-05-21T10:56:13.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-on-wed-256x256-test</loc><lastmod>2026-05-21T10:54:53.676Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/estimated-time-of-arrival-on-porto</loc><lastmod>2026-07-01T06:51:19.891Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explicit-implicit-reasoning-on-mixrea</loc><lastmod>2026-05-20T09:54:26.644Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/referring-video-object-segmentation-on-ref-ytvos</loc><lastmod>2026-05-20T09:48:02.969Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-document-understanding-on-ocrbench</loc><lastmod>2026-05-20T09:04:10.875Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/illuminant-estimation-on-nus-8-test</loc><lastmod>2026-05-20T09:04:09.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/illuminant-estimation-on-gehler-shi-test</loc><lastmod>2026-05-20T09:04:09.271Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-insulator-fault-detection-dataset</loc><lastmod>2026-05-20T09:04:08.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-asr-asr-t</loc><lastmod>2026-05-20T08:45:16.248Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-question-answering-on-gpqa-pass-at-8</loc><lastmod>2026-05-20T08:44:03.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ifeval-average-metric</loc><lastmod>2026-05-20T08:44:03.755Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-l1-l5-scores</loc><lastmod>2026-05-20T08:44:03.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-pass-at-1-pass-at-4-pass-at-8</loc><lastmod>2026-05-20T08:44:03.689Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-pass-at-8-pass-at-4-pass-at-1</loc><lastmod>2026-05-20T08:44:03.658Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-unlearning-on-mquake</loc><lastmod>2026-05-20T07:16:37.278Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/claim-correction-on-scifact-retrieved-evidence</loc><lastmod>2026-05-20T06:53:27.520Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/claim-correction-on-fever-retrieved-evidence</loc><lastmod>2026-05-20T06:53:27.413Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-sql-on-spider-2-0</loc><lastmod>2026-05-20T06:43:25.872Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-sql-on-bird-model-execution-accuracy</loc><lastmod>2026-05-20T06:43:25.829Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/election-auditing-sample-size-estimation-on-california-election-ca</loc><lastmod>2026-05-19T13:43:15.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/election-auditing-sample-size-simulation-on-georgia-ga-simulation</loc><lastmod>2026-05-19T13:43:15.226Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/election-auditing-sample-size-simulation-on-connecticut-ct-simulation</loc><lastmod>2026-05-19T13:43:15.191Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/election-auditing-sample-size-simulation-on-1-million-district-simulation</loc><lastmod>2026-05-19T13:43:15.154Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/election-auditing-sample-size-simulation-on-congressional-district-simulation</loc><lastmod>2026-05-19T13:43:15.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-classification-on-153-datasets-shared-coverage-v1-single-seed</loc><lastmod>2026-05-19T13:43:15.042Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-language-model-evaluation-on-aggregated-11-benchmark-suite-math-code-if</loc><lastmod>2026-05-21T10:31:54.187Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-video-generation-on-narrlv</loc><lastmod>2026-05-19T12:46:42.952Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-awakening-on-imagenette-and-harmful-concepts-quantitative-assessment-200-images-per-concept</loc><lastmod>2026-05-19T12:42:55.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-healthver</loc><lastmod>2026-05-19T12:18:12.866Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-classification-on-crowd-envent</loc><lastmod>2026-05-19T12:18:12.832Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-data-generation-on-checkerboard-forbidden-cell-fraction</loc><lastmod>2026-05-19T11:23:08.566Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/distributional-fidelity-on-gaussian-mixture-model-gmm</loc><lastmod>2026-05-19T11:23:08.525Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generative-modeling-on-checkerboard-held-out-reference</loc><lastmod>2026-05-19T11:23:08.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-epf</loc><lastmod>2026-05-19T11:23:08.069Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-pass-at-1-pass-at-2</loc><lastmod>2026-05-19T11:22:31.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-pass-at-1-pass-at-2</loc><lastmod>2026-05-19T11:22:31.824Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-pass-at-1-pass-at-2</loc><lastmod>2026-05-19T11:22:31.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-accuracy-token-usage-compression-ratio</loc><lastmod>2026-05-19T10:32:16.632Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-accuracy-token-usage-compression</loc><lastmod>2026-05-19T10:32:16.597Z</lastmod></url></urlset>