<?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/physical-red-teaming-on-redvla-cumulative-level-scenarios</loc><lastmod>2026-04-27T07:39:51.156Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physical-red-teaming-on-redvla-state-level-scenarios</loc><lastmod>2026-04-27T07:39:51.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-stl-10-accm-and-p-value-evaluation</loc><lastmod>2026-04-27T07:29:49.103Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-accm-p-value</loc><lastmod>2026-04-27T07:29:49.054Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/collaborative-filtering-on-baby-r-at-20-n-at-20</loc><lastmod>2026-04-27T07:29:48.969Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/collaborative-filtering-on-electronics-r-at-20-n-at-20</loc><lastmod>2026-04-27T07:29:48.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-multi-image-understanding-on-vlm2-bench</loc><lastmod>2026-04-27T07:23:32.489Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sign-language-translation-on-phoenix14t</loc><lastmod>2026-04-27T07:19:44.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-xsum-rouge-l-factkb-bert-p</loc><lastmod>2026-04-27T07:09:41.770Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-cnn-dm-rouge-l-factkb-bert-p</loc><lastmod>2026-04-27T07:09:41.722Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/universal-multimodal-retrieval-on-mmeb-full-v2-test</loc><lastmod>2026-04-27T07:09:40.324Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-video-retrieval-on-mmeb-video-v2-test</loc><lastmod>2026-04-27T07:03:21.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-retrieval-on-mmeb-image-v2-test</loc><lastmod>2026-04-27T07:03:21.585Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-to-code-generation-on-chartx-full-test</loc><lastmod>2026-04-27T06:59:37.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-to-code-generation-on-chartmimic-full-test</loc><lastmod>2026-04-27T06:59:36.995Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-document-level-medium-resource-x-en-24-plus-plus</loc><lastmod>2026-04-27T06:32:28.016Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-document-level-medium-resource-en-x-24-plus-plus</loc><lastmod>2026-04-27T06:32:27.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-document-level-high-resource-en-x-24-plus-plus</loc><lastmod>2026-04-27T06:32:27.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-document-level-24-plus-plus-resource-groupings</loc><lastmod>2026-04-27T06:32:27.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-proof-generation-and-verification-time</loc><lastmod>2026-04-27T06:29:26.095Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continual-learning-on-cifar-100-split-10-task-test</loc><lastmod>2026-04-27T06:29:25.543Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-manipulation-on-rlbench-specific-skill-subset-with-s-r-and-vgs</loc><lastmod>2026-04-24T08:54:39.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-image-detection-on-dmimage-overall</loc><lastmod>2026-05-29T10:51:48.443Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-event-extraction-on-news-reports-dataset-test</loc><lastmod>2026-04-24T08:51:06.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-unit-test-generation-on-eidbench</loc><lastmod>2026-04-24T08:45:02.337Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-depth-estimation-on-eth3d</loc><lastmod>2026-05-21T12:45:04.402Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/probabilistic-hull-finding-on-acas-xu</loc><lastmod>2026-04-24T08:26:51.347Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/probabilistic-safety-verification-on-acas-xu-property-p2</loc><lastmod>2026-04-24T08:26:51.311Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ct-reconstruction-on-ood-dataset</loc><lastmod>2026-04-24T08:22:48.763Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-chart-question-answering-on-polychartqa-human-authored</loc><lastmod>2026-04-24T08:03:31.392Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-question-answering-on-polychartqa-mlm-generated-questions</loc><lastmod>2026-04-24T08:03:31.363Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/referring-expression-comprehension-on-vrsbench</loc><lastmod>2026-04-24T07:50:51.826Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-stl10-noise-test</loc><lastmod>2026-04-24T07:40:44.631Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-stl10-rotation-test</loc><lastmod>2026-04-24T07:40:44.580Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/behavioral-similarity-analysis-on-bench-and-2-bench-test</loc><lastmod>2026-04-24T07:30:07.688Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/script-generation-on-narrative-generation-dataset-script</loc><lastmod>2026-04-24T07:29:37.473Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/storyline-generation-on-narrative-generation-storyline</loc><lastmod>2026-04-24T07:29:37.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-tracking-on-mvot</loc><lastmod>2026-04-24T06:58:37.320Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-tracking-on-ootb</loc><lastmod>2026-04-24T06:58:37.281Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-question-answering-on-nq-triviaqa-and-webq-test</loc><lastmod>2026-04-24T06:58:36.128Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-evaluation-on-red-queen-set</loc><lastmod>2026-04-23T11:28:29.152Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/expansion-count-reduction-on-modena-osmnx-road-network-30k</loc><lastmod>2026-04-23T11:18:24.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-biomedical-domain-average-of-10-datasets-test</loc><lastmod>2026-04-23T11:03:03.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-11-natural-domain-datasets-average</loc><lastmod>2026-04-23T11:03:02.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-overall-aggregated</loc><lastmod>2026-04-23T11:00:30.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiad-pass-at-1-avgtoken</loc><lastmod>2026-04-23T11:00:30.763Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-pass-at-1-avgtoken</loc><lastmod>2026-04-23T11:00:30.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-rotated-fmnist</loc><lastmod>2026-04-23T10:58:29.263Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-pro-maj-at-2-maj-at-4-maj-at-8</loc><lastmod>2026-04-23T10:51:23.266Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detective-puzzle-reasoning-on-dp-complex</loc><lastmod>2026-04-23T10:46:49.952Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detective-puzzle-reasoning-on-dp-medium</loc><lastmod>2026-04-23T10:46:49.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detective-puzzle-reasoning-on-dp-easy</loc><lastmod>2026-04-23T10:46:49.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bimanual-robot-manipulation-on-twin-1-0-test</loc><lastmod>2026-04-23T10:42:13.666Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-atir-a-t-test</loc><lastmod>2026-04-23T10:33:06.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-verification-on-unstable-1d-system</loc><lastmod>2026-04-23T10:24:01.181Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grounded-multimodal-named-entity-recognition-on-twitter-fmnerg</loc><lastmod>2026-04-23T10:18:03.594Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-nek</loc><lastmod>2026-04-23T10:14:54.290Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-yahoo</loc><lastmod>2026-04-23T10:14:54.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-iops</loc><lastmod>2026-04-23T10:14:54.220Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/univariate-anomaly-detection-on-msl</loc><lastmod>2026-04-23T10:14:54.000Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spectral-image-reconstruction-on-arad_1k</loc><lastmod>2026-07-01T06:44:16.057Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hdr-imaging-on-si-hdr-fast-synthetic-handheld-simulator</loc><lastmod>2026-04-23T09:30:56.708Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-retrieval-and-reasoning-on-ruler-128k-context</loc><lastmod>2026-04-23T09:18:19.915Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/repository-level-code-completion-on-repobench-p-128k-context</loc><lastmod>2026-04-23T09:18:19.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-qasper-128k-context</loc><lastmod>2026-04-23T09:18:19.849Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-text-summarization-on-multinews-128k-context</loc><lastmod>2026-04-23T09:18:19.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cardiac-ultrasound-segmentation-on-camus</loc><lastmod>2026-04-23T09:08:44.496Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optic-cup-segmentation-on-refuge2-cup</loc><lastmod>2026-04-23T09:08:44.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optic-disc-segmentation-on-refuge2-disc</loc><lastmod>2026-04-23T09:08:44.422Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-fleurs-s2tt-test</loc><lastmod>2026-04-23T09:00:39.870Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-on-storyeval-bench</loc><lastmod>2026-04-23T08:48:32.228Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-to-video-generation-on-storyeval-bench-i2v</loc><lastmod>2026-04-23T08:48:32.182Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuum-field-reconstruction-on-shallow-water-avg</loc><lastmod>2026-04-23T08:42:24.790Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuum-field-reconstruction-on-shallow-water-out-t</loc><lastmod>2026-04-23T08:42:24.756Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuum-field-reconstruction-on-shallow-water-in-t</loc><lastmod>2026-04-23T08:42:24.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuum-field-reconstruction-on-ns-1e-5-avg</loc><lastmod>2026-04-23T08:42:24.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuum-field-reconstruction-on-ns-nu-1e-5-in-t</loc><lastmod>2026-04-23T08:42:24.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuum-field-reconstruction-rollout-on-2d-navier-stokes-nu-1e-5</loc><lastmod>2026-04-23T08:42:24.571Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-browsing-and-navigation-on-browsecomp</loc><lastmod>2026-04-23T08:33:20.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-forgery-detection-on-trace-test</loc><lastmod>2026-04-23T08:31:48.963Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-generation-on-vicuna</loc><lastmod>2026-04-23T07:42:39.821Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-generation-on-dolly</loc><lastmod>2026-04-23T07:42:39.767Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-qa-on-supergpqa</loc><lastmod>2026-04-23T07:42:39.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-qa-on-mmlu-pro</loc><lastmod>2026-04-23T07:42:39.684Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-qa-on-csqa</loc><lastmod>2026-04-23T07:42:39.655Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-bigmath-level-5</loc><lastmod>2026-04-23T07:42:39.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-bigmath-level-4</loc><lastmod>2026-04-23T07:42:39.581Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/employee-morale-prediction-on-firm-posts-dataset-tmax-15-posts-threshold</loc><lastmod>2026-04-23T07:38:07.241Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/roa-prediction-on-firm-posts-dataset-tmax-15-posts-threshold</loc><lastmod>2026-04-23T07:38:07.149Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-hallucination-evaluation-on-pope-concurrence</loc><lastmod>2026-04-23T06:56:49.722Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-gpqa-diamond</loc><lastmod>2026-04-21T13:39:30.732Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-s-and-p-500-four-time-intervals-ahead</loc><lastmod>2026-04-21T13:16:32.772Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-cross-rate-four-time-intervals-ahead</loc><lastmod>2026-04-21T13:16:32.684Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-accuracy-f1-score-recall-precision</loc><lastmod>2026-04-21T13:06:30.222Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/exact-match-performance-on-big-bench-hard-bbh</loc><lastmod>2026-04-21T12:59:38.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/defect-detection-on-codexglue-defect-detection-test</loc><lastmod>2026-04-21T12:50:31.792Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clone-detection-on-codexglue-clone-detection</loc><lastmod>2026-04-21T12:50:31.661Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/defect-detection-on-codexglue-defect-detection</loc><lastmod>2026-04-21T12:50:31.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-language-understanding-on-qwen-multi-task-evaluation-suite-2-5-test</loc><lastmod>2026-04-21T12:38:24.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-question-answering-on-docvqa-score</loc><lastmod>2026-05-13T08:12:51.419Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toxicity-classification-on-toxic</loc><lastmod>2026-07-08T07:50:00.934Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generative-hallucination-mitigation-on-object-halbench-test</loc><lastmod>2026-04-21T12:26:20.239Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-search-on-xbench-deepsearch-2505</loc><lastmod>2026-04-21T12:16:17.779Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-on-code-humaneval-plus-livecodebench-v5</loc><lastmod>2026-04-21T12:16:17.155Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physics-reasoning-on-physics-c-eval-webinstruct</loc><lastmod>2026-04-21T12:16:17.120Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-reasoning-on-medbullets-and-medxqa</loc><lastmod>2026-04-21T12:16:17.077Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-loop-planning-on-nuscenes-open-loop-evaluation</loc><lastmod>2026-04-21T12:16:15.992Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-mmlu-auroc-tier-and-r</loc><lastmod>2026-04-21T11:46:07.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-video-question-answering-on-shortvid-bench</loc><lastmod>2026-04-21T11:25:59.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/omnimodal-audio-and-video-question-answering-on-avutbench</loc><lastmod>2026-04-21T11:18:54.768Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/source-code-watermarking-on-mbpp-with-codebleu</loc><lastmod>2026-04-21T11:15:56.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relevance-assessment-on-t2ranking-test</loc><lastmod>2026-04-21T10:57:04.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relevance-assessment-on-noterel-test</loc><lastmod>2026-04-21T10:57:04.181Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-visual-question-answering-on-mmbench</loc><lastmod>2026-06-01T09:18:27.909Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/t2i-metric-evaluation-on-crocsyn-inverse-image-based</loc><lastmod>2026-04-21T10:45:48.352Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/t2i-metric-evaluation-on-crocsyn-forward-image-based</loc><lastmod>2026-04-21T10:45:48.318Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/t2i-metric-evaluation-on-crocsyn-inverse-text-based</loc><lastmod>2026-04-21T10:45:48.282Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/t2i-metric-evaluation-on-crocsyn-forward-text-based</loc><lastmod>2026-04-21T10:45:48.245Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-optimization-linear-and-convex-quadratic-constraints-on-optimization-te2-out-of-distribution-test</loc><lastmod>2026-04-21T10:36:52.267Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-optimization-linear-and-convex-quadratic-constraints-on-optimization-2-te2-in-distribution-test</loc><lastmod>2026-04-21T10:36:52.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-c-l5-imbalanced-labels</loc><lastmod>2026-04-21T10:35:44.417Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-c-level-5-test</loc><lastmod>2026-04-21T10:35:44.368Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polyp-segmentation-on-average-across-domains-a-d-test</loc><lastmod>2026-04-21T10:26:41.846Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polyp-segmentation-on-cvc-colondb-domain-d-test</loc><lastmod>2026-04-21T10:26:41.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polyp-segmentation-on-etis-laribpolypdb-domain-c-test</loc><lastmod>2026-04-21T10:26:41.709Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polyp-segmentation-on-kvasir-seg-domain-b-test</loc><lastmod>2026-04-21T10:26:41.667Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polyp-segmentation-on-cvc-clinicdb-domain-a-test</loc><lastmod>2026-04-21T10:26:41.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-tofu-log-scaled-forget-quality-metrics</loc><lastmod>2026-04-21T10:25:39.524Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-question-answering-on-scienceqa-image</loc><lastmod>2026-06-18T07:46:15.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deepfake-detection-on-deepfake-detection-challenge-preview-dfdcp</loc><lastmod>2026-04-21T10:09:27.548Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-attribution-on-ua-bench-reasoning-intensive-tasks</loc><lastmod>2026-04-21T10:05:33.537Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-attribution-on-ua-bench-knowledge-intensive-tasks</loc><lastmod>2026-04-21T10:05:33.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-agent-task-on-scienceworld-unseen</loc><lastmod>2026-04-21T10:05:32.128Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-agent-task-on-scienceworld-seen</loc><lastmod>2026-04-21T10:05:32.090Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-agent-task-on-virtualhome-unseen</loc><lastmod>2026-04-21T10:05:32.045Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/success-rate-percent-on-alfworld-seen</loc><lastmod>2026-04-21T10:05:31.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-task-completion-on-jericho</loc><lastmod>2026-04-21T10:05:31.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-task-completion-on-scienceworld</loc><lastmod>2026-04-21T10:05:31.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-task-completion-on-alfworld</loc><lastmod>2026-04-21T10:05:31.786Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-completion-on-tw-express</loc><lastmod>2026-04-21T10:05:31.744Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-task-completion-on-textworld</loc><lastmod>2026-04-21T10:05:31.706Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intervention-on-cogbiasesc-test</loc><lastmod>2026-04-21T09:55:29.149Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cognitive-distortion-diagnose-on-cogbiasesc-test</loc><lastmod>2026-04-21T09:55:29.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inference-efficiency-on-general-llm-prompts</loc><lastmod>2026-04-21T09:48:14.790Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/malicious-query-safety-evaluation-on-jailbench</loc><lastmod>2026-04-21T09:48:14.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/malicious-query-safety-evaluation-on-advbench</loc><lastmod>2026-04-21T09:48:14.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/streaming-video-understanding-on-streambench</loc><lastmod>2026-06-19T07:49:16.780Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/path-planning-on-synthetic</loc><lastmod>2026-04-21T09:27:28.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/path-planning-on-pastis</loc><lastmod>2026-04-21T09:27:28.606Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/climate-discovery-on-climabench-2025</loc><lastmod>2026-04-21T09:15:49.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/climate-discovery-on-climabench-2000-2024</loc><lastmod>2026-04-21T09:15:49.701Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-classification-on-vindr-pcxr</loc><lastmod>2026-04-21T08:56:38.324Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-classification-on-derma</loc><lastmod>2026-04-21T08:56:38.266Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-writing-on-longbench-write</loc><lastmod>2026-04-21T08:47:02.143Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-writing-on-creative-w-b</loc><lastmod>2026-04-21T08:47:02.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-writing-on-writingbench</loc><lastmod>2026-04-21T08:47:02.086Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-c-memory-and-energy-usage</loc><lastmod>2026-04-21T08:42:27.799Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-flowverse-vision-primary</loc><lastmod>2026-04-21T08:41:57.141Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-flowverse-vision-centric</loc><lastmod>2026-04-21T08:41:57.103Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-flowverse-vision-dense</loc><lastmod>2026-04-21T08:41:57.052Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-flowverse-text-limited</loc><lastmod>2026-04-21T08:41:56.973Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-flowverse-all</loc><lastmod>2026-04-21T08:41:56.867Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/camouflaged-object-detection-on-camo-test-s_alpha-f_w_beta-e_m-f_m_beta-mae</loc><lastmod>2026-04-21T08:21:43.008Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-time-series-forecasting-on-etth1-average</loc><lastmod>2026-05-19T11:23:08.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-full-slice</loc><lastmod>2026-04-21T07:55:58.772Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-open-augmented-full-slice</loc><lastmod>2026-04-21T07:55:58.740Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/accuracy-on-nq-val</loc><lastmod>2026-04-21T07:55:58.705Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpots</loc><lastmod>2026-04-21T07:55:58.677Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotd-accuracy</loc><lastmod>2026-04-21T07:55:58.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-synth</loc><lastmod>2026-04-21T07:55:58.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-helpful</loc><lastmod>2026-04-21T07:55:58.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-distractor-hard</loc><lastmod>2026-04-21T07:55:58.581Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-restate-hard</loc><lastmod>2026-04-21T07:55:58.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-question-answering-on-expertqa</loc><lastmod>2026-04-21T07:55:58.523Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-summarization-on-tofueval</loc><lastmod>2026-04-21T07:55:58.485Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-quantification-on-libero-object-test</loc><lastmod>2026-04-21T07:54:49.940Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/message-parsing-on-cbrs-bn</loc><lastmod>2026-04-21T07:54:49.768Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-structural-elucidation-on-nplib1</loc><lastmod>2026-04-21T07:50:25.321Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-mllm-safety-evaluation-on-steer-average-multi-turn</loc><lastmod>2026-04-21T07:14:38.211Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-mllm-safety-evaluation-on-steer-dys-multi-turn</loc><lastmod>2026-04-21T07:14:38.180Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-mllm-safety-evaluation-on-steer-spa-multi-turn</loc><lastmod>2026-04-21T07:14:38.152Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-mllm-safety-evaluation-on-steer-vls-multi-turn</loc><lastmod>2026-04-21T07:14:38.120Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-mllm-safety-evaluation-on-steer-mmsafe-multi-turn</loc><lastmod>2026-04-21T07:14:38.088Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-mllm-safety-evaluation-on-steer-beaver-multi-turn</loc><lastmod>2026-04-21T07:14:38.058Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-vlsbench</loc><lastmod>2026-04-21T07:14:38.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-mm-safety</loc><lastmod>2026-04-21T07:14:37.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-beavertails</loc><lastmod>2026-04-21T07:14:37.859Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bayesian-assessment-of-sycophancy-on-basil-user-belief-setting-1-0-test</loc><lastmod>2026-04-21T07:04:33.714Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bayesian-assessment-of-sycophancy-on-basil-third-p-belief-setting-1-0-test</loc><lastmod>2026-04-21T07:04:33.684Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bayesian-assessment-of-sycophancy-on-basil-abstract-setting-1-0-test</loc><lastmod>2026-04-21T07:04:33.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/downstream-rag-utility-on-filice-et-al-unseen-open-ended</loc><lastmod>2026-04-21T07:04:33.207Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/downstream-rag-utility-on-filice-et-al-unseen-complex</loc><lastmod>2026-04-21T07:04:33.179Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/downstream-rag-utility-on-filice-unseen-comparison</loc><lastmod>2026-04-21T07:04:33.140Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/downstream-rag-utility-on-unseen-multi-aspect</loc><lastmod>2026-04-21T07:04:33.097Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/downstream-rag-utility-on-filice-balanced</loc><lastmod>2026-04-21T07:04:33.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerability-detection-validation-on-16-open-source-repositories-rust-python-php-ruby</loc><lastmod>2026-04-20T08:23:53.413Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/modality-transfer-on-fibroblast-cells-test</loc><lastmod>2026-04-20T08:14:19.090Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-acc-delta_up-delta_down</loc><lastmod>2026-04-20T08:14:15.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-acc-delta_up-delta_down</loc><lastmod>2026-04-20T08:14:15.026Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-acc-delta_up-delta_down</loc><lastmod>2026-04-20T08:14:14.994Z</lastmod></url></urlset>