<?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/fraud-detection-on-digitalmusic</loc><lastmod>2026-02-26T05:51:31.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fraud-detection-on-instantvideo</loc><lastmod>2026-02-26T05:51:31.908Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/legal-question-answering-on-jec-qa</loc><lastmod>2026-02-26T05:47:42.007Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aggregate-aime24-amc-math500-minerva-olympiad-bench</loc><lastmod>2026-02-26T05:34:36.260Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-level-confidence-prediction-on-fever</loc><lastmod>2026-05-13T07:38:59.745Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-average-across-all-benchmarks</loc><lastmod>2026-03-19T09:19:13.689Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-p-at-1-p-at-16</loc><lastmod>2026-02-26T05:54:45.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-p-at-1-and-p-at-16</loc><lastmod>2026-02-26T06:11:13.944Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-p-at-1-p-at-16</loc><lastmod>2026-02-26T05:54:45.902Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-p-at-1-and-p-at-16</loc><lastmod>2026-02-26T06:11:13.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-performance-on-acebench-agent</loc><lastmod>2026-02-26T05:42:00.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-math-reasoning-long-q-long-a-test</loc><lastmod>2026-02-26T05:57:24.476Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-qa-on-long-form-qa-short-q-long-a-test</loc><lastmod>2026-02-26T05:45:47.539Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-summarization-long-q-short-a-test</loc><lastmod>2026-02-26T06:00:36.657Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-machine-translation-short-q-short-a-test</loc><lastmod>2026-02-26T05:37:01.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-recognition-on-mcv-unseen-accents-100h-test</loc><lastmod>2026-02-26T05:22:25.656Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-recognition-on-mcv-seen-accents-100h-test</loc><lastmod>2026-02-26T05:42:21.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-agi-eval-en</loc><lastmod>2026-02-27T10:43:54.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-multifieldqa-accuracy</loc><lastmod>2026-02-26T05:30:53.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-assistant-tasks-on-gaia</loc><lastmod>2026-02-26T06:05:10.050Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-understanding-on-glue-full-suite</loc><lastmod>2026-02-26T05:39:26.981Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-mathvista</loc><lastmod>2026-02-26T05:45:45.203Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-safety-detection-on-wildguardmix-train</loc><lastmod>2026-02-26T05:26:05.561Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-safety-detection-on-wildguardmix-test</loc><lastmod>2026-02-26T05:26:05.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-understanding-on-cv-bench</loc><lastmod>2026-05-12T09:51:10.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/political-stance-detection-on-forum-dataset-200-post-test</loc><lastmod>2026-02-26T05:30:51.829Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-wikipedia-spinbot-paraphrased-test</loc><lastmod>2026-02-26T05:43:55.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-theses-spinbot-paraphrased-test</loc><lastmod>2026-02-26T05:43:55.802Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-arxiv-spinbot-paraphrased-test</loc><lastmod>2026-02-26T05:42:51.238Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-understanding-on-longvideobench-lvb</loc><lastmod>2026-06-24T07:57:19.210Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-quality-evaluation-on-openaudiobench-english-subsets-test</loc><lastmod>2026-02-26T06:08:29.144Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-quality-evaluation-on-openaudiobench-english-subsets-test</loc><lastmod>2026-02-26T05:34:52.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/efficiency-evaluation-on-openaudiobench-english-subsets-test</loc><lastmod>2026-02-26T06:06:00.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotional-support-conversation-on-extes-test</loc><lastmod>2026-02-26T05:37:16.635Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/community-notes-generation-on-polbench-test</loc><lastmod>2026-02-26T05:53:58.848Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-mmlu-pro-accuracy-and-resource-usage</loc><lastmod>2026-05-11T07:10:16.045Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-accuracy-and-token-costs</loc><lastmod>2026-02-26T06:03:39.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-accuracy-and-token-costs</loc><lastmod>2026-02-26T06:03:39.611Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-boundary-expression-on-cflue-test</loc><lastmod>2026-02-26T05:43:30.489Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-boundary-expression-on-mmedbench-test</loc><lastmod>2026-02-26T05:43:30.332Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-reasoning-on-gpqa-diamond</loc><lastmod>2026-03-18T08:20:48.952Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/layout-generation-on-greenpd-1-0-test</loc><lastmod>2026-02-26T05:44:34.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-environment-task-execution-on-appworld-normal-test</loc><lastmod>2026-03-31T09:22:08.229Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relevance-on-hotpotqa</loc><lastmod>2026-02-26T05:47:52.870Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relevance-on-alce</loc><lastmod>2026-02-26T05:47:52.853Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-text-evaluation-on-amazon-mae-mse</loc><lastmod>2026-02-26T05:49:09.874Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-text-evaluation-on-relish</loc><lastmod>2026-02-26T06:09:38.600Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-text-evaluation-on-asap</loc><lastmod>2026-02-26T05:59:08.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-avg-at-8-avg-at-16-avg-at-32</loc><lastmod>2026-03-20T08:56:44.111Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-long-term-forecasting-on-illness-v1-test</loc><lastmod>2026-02-26T05:50:53.062Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-arm-manipulation-on-metaworld-easy</loc><lastmod>2026-02-26T06:05:18.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/entity-alignment-on-dwy100k-wd</loc><lastmod>2026-02-26T05:46:35.683Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/penetration-testing-on-real-world-enterprise-penetration-testing-environment</loc><lastmod>2026-02-26T06:07:26.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-conspiratorial-content-dataset</loc><lastmod>2026-02-26T05:30:47.979Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-making-on-webshop</loc><lastmod>2026-03-10T13:39:44.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-research-on-xbench-deepsearch-original-test</loc><lastmod>2026-02-26T05:57:23.633Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-scoring-on-security-scenario</loc><lastmod>2026-02-26T05:35:50.448Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-scoring-on-science-scenario</loc><lastmod>2026-02-26T05:36:30.160Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-scoring-on-data-scenario</loc><lastmod>2026-02-26T05:35:50.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-scoring-on-software-scenario</loc><lastmod>2026-02-26T05:35:50.411Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-routing-on-security</loc><lastmod>2026-02-26T05:39:57.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-routing-on-science</loc><lastmod>2026-02-26T05:39:57.422Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-routing-on-data</loc><lastmod>2026-02-26T05:39:57.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-question-answering-on-recap-coco</loc><lastmod>2026-02-26T05:38:43.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-phd</loc><lastmod>2026-02-26T05:38:43.910Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-question-answering-on-scienceqa-cp-asr</loc><lastmod>2026-02-26T05:39:52.834Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recidivism-prediction-on-nlsy97</loc><lastmod>2026-02-26T05:24:49.351Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cancer-indication-prediction-on-msk-cohort-oncology</loc><lastmod>2026-02-26T05:25:33.014Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-search-on-xbench</loc><lastmod>2026-02-26T05:35:50.331Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-execution-on-virtualhome-unseen-domains</loc><lastmod>2026-02-26T06:05:08.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mobile-gui-agent-execution-on-androidcontrol-curated-easy</loc><lastmod>2026-02-26T06:07:45.553Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mobile-gui-agent-execution-on-androidcontrol-curated-hard</loc><lastmod>2026-02-26T06:07:45.445Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-abcd-anx</loc><lastmod>2026-02-26T05:30:44.063Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/brain-network-classification-on-ppmi</loc><lastmod>2026-02-26T05:43:29.796Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/brain-network-classification-on-abcd-anx</loc><lastmod>2026-02-26T05:43:29.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/brain-network-classification-on-abcd-adhd</loc><lastmod>2026-02-26T05:43:29.758Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-levels-3-4-5-test</loc><lastmod>2026-05-19T09:48:34.178Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adl-recognition-on-casas-milan</loc><lastmod>2026-02-26T06:08:47.225Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-pubmedqa-accuracy-and-ece</loc><lastmod>2026-04-08T07:48:47.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-tool-calling-on-bfcl-v4-val</loc><lastmod>2026-02-26T05:54:25.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-jailbreak-defense-on-video-safetybench-benign-queries</loc><lastmod>2026-02-26T05:24:03.752Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-jailbreak-defense-on-video-safetybench-harmful-queries</loc><lastmod>2026-02-26T05:21:37.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-out-of-domain-val-test</loc><lastmod>2026-02-26T05:42:30.174Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-out-of-domain-val-test</loc><lastmod>2026-02-26T05:42:30.159Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-out-of-domain-val-test</loc><lastmod>2026-02-26T05:42:30.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-in-domain-val-test</loc><lastmod>2026-02-26T05:42:30.128Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-question-answering-on-popqa-out-of-domain-val-test</loc><lastmod>2026-02-26T05:42:30.113Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-oriented-multi-agent-communication-on-mmlu-arc-c-gsm8k-openbookqa-medqa-average-test</loc><lastmod>2026-02-26T05:30:42.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/two-agent-cooperation-on-c-wah</loc><lastmod>2026-02-26T06:07:29.729Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyper-relational-inductive-link-prediction-on-wdsplit100-v2</loc><lastmod>2026-02-26T05:50:31.655Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyper-relational-inductive-link-prediction-on-wd20k33-v2</loc><lastmod>2026-02-26T05:50:31.639Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyper-relational-inductive-link-prediction-on-wdsplit100-v1</loc><lastmod>2026-02-26T05:50:31.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyper-relational-link-prediction-on-wd20k100-v1</loc><lastmod>2026-02-26T05:50:31.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speculative-decoding-efficiency-on-cnn-dm-gsm8k-tinystories-aggregate</loc><lastmod>2026-02-26T05:40:34.390Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-generation-on-tinystories-21-test</loc><lastmod>2026-02-26T06:04:42.789Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-20-test</loc><lastmod>2026-02-26T06:04:42.775Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-cnn-daily-mail-19-test</loc><lastmod>2026-02-26T06:04:42.758Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/training-throughput-measurement-on-maniskill</loc><lastmod>2026-02-26T06:07:34.981Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-ai-assistant-task-completion-on-gaia-text-only</loc><lastmod>2026-02-26T05:30:42.340Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sleep-stage-classification-on-shhs1-test</loc><lastmod>2026-05-11T07:20:51.604Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scenario-based-reasoning-overall-on-tsrbench</loc><lastmod>2026-02-26T05:54:25.351Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inferential-calculation-on-tsrbench</loc><lastmod>2026-02-26T05:30:41.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scenario-attribution-on-tsrbench</loc><lastmod>2026-02-26T05:30:41.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-tsrbench</loc><lastmod>2026-02-26T05:30:41.709Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-driving-on-nocrash-town02</loc><lastmod>2026-02-26T06:02:12.915Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-faithfulness-evaluation-on-seetrue</loc><lastmod>2026-02-26T05:43:29.274Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ai-generated-content-evaluation-on-agin</loc><lastmod>2026-02-26T05:43:29.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-failure-prediction-and-selective-task-completion-on-tau2-bench-telecom-1-0</loc><lastmod>2026-02-26T05:26:04.418Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-failure-prediction-and-selective-task-completion-on-tau2-bench-retail-1-0</loc><lastmod>2026-02-26T05:26:04.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-failure-prediction-and-selective-completion-on-tau2-bench-airline-1-0</loc><lastmod>2026-02-26T05:26:04.375Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lossless-data-compression-on-enwik8</loc><lastmod>2026-03-11T06:47:42.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-average</loc><lastmod>2026-02-26T05:36:11.162Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-11</loc><lastmod>2026-02-26T05:43:29.167Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-10</loc><lastmod>2026-02-26T05:43:52.776Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-9</loc><lastmod>2026-02-26T05:43:29.149Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-8</loc><lastmod>2026-02-26T05:43:29.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-7</loc><lastmod>2026-02-26T05:43:29.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-6</loc><lastmod>2026-02-26T05:43:29.098Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-5</loc><lastmod>2026-02-26T05:43:52.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-4</loc><lastmod>2026-02-26T05:43:57.881Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-3</loc><lastmod>2026-02-26T05:43:29.080Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-2</loc><lastmod>2026-02-26T05:43:29.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/driver-drowsiness-detection-on-sustained-attention-driving-dataset-subject-1</loc><lastmod>2026-02-26T05:43:29.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-yaleb</loc><lastmod>2026-06-04T10:27:49.499Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-webkb4</loc><lastmod>2026-06-04T10:27:49.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-200-top-1-and-top-5-accuracy</loc><lastmod>2026-03-04T07:23:12.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sketch-based-image-retrieval-on-quickdraw</loc><lastmod>2026-02-26T06:09:38.548Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sketch-based-image-retrieval-on-tu-berlin</loc><lastmod>2026-02-26T06:09:38.532Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sketch-based-image-retrieval-on-sketchy</loc><lastmod>2026-02-26T06:10:03.241Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-foggy-cityscapes-full-val</loc><lastmod>2026-02-26T05:23:08.300Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/talking-head-generation-on-celebv-hq</loc><lastmod>2026-05-19T09:03:35.200Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instance-image-goal-navigation-on-hm3d-v3-val</loc><lastmod>2026-02-26T06:05:39.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-scienceworld-unseen</loc><lastmod>2026-06-04T07:54:23.667Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-person-re-identification-on-rstpreid-coarse-grained-test</loc><lastmod>2026-02-26T06:01:04.565Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-person-re-identification-on-icfg-pedes-coarse-grained-test</loc><lastmod>2026-02-26T06:01:04.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-based-person-re-identification-on-cuhk-pedes-coarse-grained-test</loc><lastmod>2026-02-26T06:01:04.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-state-transition-on-pfdial-ood-test</loc><lastmod>2026-02-26T05:26:45.243Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backward-transition-handling-on-pfdial-h-test</loc><lastmod>2026-02-26T05:30:38.739Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-on-advbench-ensemble-configuration-average</loc><lastmod>2026-02-26T05:46:23.660Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-on-advbench-ensemble-configuration-llama-3-70b</loc><lastmod>2026-02-26T05:46:23.641Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-evaluation-on-advbench-ensemble-configuration-claude-v2</loc><lastmod>2026-02-26T05:46:23.620Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-video-understanding-on-lvbench-val</loc><lastmod>2026-02-26T06:03:48.693Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-touche-beir-2020-test</loc><lastmod>2026-04-13T10:11:11.450Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-hallucination-evaluation-on-coco</loc><lastmod>2026-02-26T05:38:19.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/in-context-learning-on-9-dataset-average-sst-5-mnli-cmsqa-hellaswag-geoq-nl2bash-break-mtop-smcalflow-test</loc><lastmod>2026-02-26T05:30:37.657Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-cityscapes-synthetic-to-real-v1-0-test</loc><lastmod>2026-02-26T05:23:19.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-realworldqa-1-0-test</loc><lastmod>2026-02-26T05:30:37.558Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-level-object-discovery-on-coco</loc><lastmod>2026-02-26T06:10:35.840Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-label-classification-on-dgm4-entire-dataset-1-0-test</loc><lastmod>2026-02-26T06:09:41.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-grounding-on-dgm4-image-sub-dataset-1-0-test</loc><lastmod>2026-02-26T05:47:29.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-test-accuracy-and-hardware-consumption</loc><lastmod>2026-02-26T05:33:57.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/photo-sketch-matching-on-psc6k-test</loc><lastmod>2026-02-26T05:54:57.634Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-scene-generation-on-3d-front-livingroom-test</loc><lastmod>2026-06-09T10:57:11.520Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-text-retrieval-on-objaverse-lvis-1-0-test</loc><lastmod>2026-02-26T05:38:33.696Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-text-matching-on-objaverse-lvis-1-0-test</loc><lastmod>2026-02-26T05:38:28.439Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-m3sciqa</loc><lastmod>2026-03-04T13:13:05.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-halueval-component-metrics</loc><lastmod>2026-04-06T08:36:39.265Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-wordnet-test</loc><lastmod>2026-02-26T05:30:35.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-semeval-food-2016-test</loc><lastmod>2026-02-26T05:30:35.941Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-f1-score-only</loc><lastmod>2026-02-26T05:43:28.132Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-acdc-v1-test</loc><lastmod>2026-02-26T06:10:35.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-foggycityscapes-v1-test</loc><lastmod>2026-02-26T06:10:35.776Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overall-performance-on-must-c-and-spoken-squad</loc><lastmod>2026-02-26T05:53:41.714Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoken-question-answering-on-spoken-squad</loc><lastmod>2026-02-26T05:41:36.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-translation-on-must-c</loc><lastmod>2026-02-26T05:37:00.146Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-presence-hallucination-evaluation-on-pope-gqa-2019-random</loc><lastmod>2026-02-26T05:31:22.097Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-presence-hallucination-evaluation-on-pope-a-okvqa-popular-2022</loc><lastmod>2026-02-26T05:31:22.080Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/real-time-latency-evaluation-on-ag-news</loc><lastmod>2026-02-26T05:48:30.899Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-translation-on-fleurs-test</loc><lastmod>2026-02-26T05:38:41.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phone-recognition-on-seen-languages</loc><lastmod>2026-02-26T05:42:04.255Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-instructrec-amazon-movietv-test</loc><lastmod>2026-02-26T05:46:14.936Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-navigation-on-miniwob-plus-plus</loc><lastmod>2026-02-26T05:30:33.672Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-correspondence-on-ap-10k</loc><lastmod>2026-05-29T11:46:16.446Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-asdiv-aug-accuracy</loc><lastmod>2026-02-26T05:30:33.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuation-zero-shot-speech-synthesis-on-librispeech-test-clean</loc><lastmod>2026-02-26T06:08:38.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-capability-preservation-on-safeedit</loc><lastmod>2026-02-26T05:45:22.446Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-xiezhi-test</loc><lastmod>2026-02-26T06:04:05.666Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-average-across-general-and-medical-domains</loc><lastmod>2026-02-26T05:54:28.532Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-scifact</loc><lastmod>2026-02-26T05:37:30.424Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-summeval</loc><lastmod>2026-02-26T05:37:33.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-aggrefact-cnn</loc><lastmod>2026-02-26T05:37:30.410Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-aggrefact-xsum</loc><lastmod>2026-02-26T05:37:33.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gender-discrimination-risk-evaluation-on-occupational-contexts-test</loc><lastmod>2026-02-26T05:59:12.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/discrimination-risk-evaluation-on-occupation-based-racial-discrimination-dataset</loc><lastmod>2026-02-26T06:02:20.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-financial-phrasebank-fpb</loc><lastmod>2026-03-05T07:20:37.762Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-inference-acceleration-on-mbpp-code-llama</loc><lastmod>2026-02-26T05:49:42.783Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-event-detection-on-seoe</loc><lastmod>2026-02-26T05:58:29.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-to-image-machine-translation-on-iimt30k-tnr-de-en-test</loc><lastmod>2026-04-21T09:23:26.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/class-to-video-generation-on-ucf-101</loc><lastmod>2026-03-13T09:41:49.387Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-reconstruction-on-imagenet-512x512</loc><lastmod>2026-06-12T08:29:38.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/common-sense-reasoning-on-5-common-sense-reasoning-tasks-llama-2-70b</loc><lastmod>2026-02-26T05:35:15.099Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/common-sense-reasoning-on-5-common-sense-reasoning-tasks-llama-2-13b</loc><lastmod>2026-02-26T05:30:31.846Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-imdb-test-adversarial-robustness-via-aua-and-query-counts</loc><lastmod>2026-02-26T05:39:17.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-agnews-test-adversarial-robustness-and-query-efficiency</loc><lastmod>2026-02-26T05:34:12.618Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/referring-video-object-segmentation-on-long-rvos-val</loc><lastmod>2026-06-08T06:50:05.057Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-iirc</loc><lastmod>2026-02-26T05:41:36.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/acoustic-scene-classification-on-tut-2017</loc><lastmod>2026-06-16T08:45:07.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-rwku-llama-3-1-8b-neighbor-set</loc><lastmod>2026-02-26T05:44:03.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-object-tracking-on-mot-17-public-detections</loc><lastmod>2026-02-26T05:50:07.342Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatiotemporal-video-super-resolution-on-adobe240-center</loc><lastmod>2026-02-26T05:56:24.292Z</lastmod></url></urlset>