<?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/agent-safety-evaluation-on-agentharm-benign-requests</loc><lastmod>2026-06-02T12:37:31.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-safety-evaluation-on-agentharm-harmful-requests</loc><lastmod>2026-06-02T12:37:31.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/throughput-measurement-on-gpqa-diamond</loc><lastmod>2026-06-02T12:07:20.097Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/harmful-prompt-detection-on-simpst</loc><lastmod>2026-07-03T07:48:59.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/harmful-prompt-detection-on-harmb</loc><lastmod>2026-07-03T07:48:59.891Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ppa-model-inversion-attack-on-facescrub-224x224-private-plus-ffhq-public-test</loc><lastmod>2026-06-02T11:38:37.467Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-time-series-forecasting-on-lotka-volterra-l-v-synthetic-test</loc><lastmod>2026-06-02T11:37:09.529Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mnist-fmnist</loc><lastmod>2026-06-02T11:37:08.439Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar10-pm-and-gm-metrics</loc><lastmod>2026-06-02T11:37:08.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-fmnist-pm-gm-metrics</loc><lastmod>2026-06-02T11:37:08.360Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mnist-pm-gm</loc><lastmod>2026-06-02T11:37:08.323Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-capability-evaluation-on-arc-c-hellaswag-mmlu-gsm8k</loc><lastmod>2026-06-02T11:21:21.660Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medqa-acc-token-usage-speed</loc><lastmod>2026-07-01T07:58:55.012Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sufficient-dimension-reduction-on-synthetic-sdr-10-scenarios</loc><lastmod>2026-06-02T08:08:30.223Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sufficient-dimension-reduction-on-synthetic-sdr</loc><lastmod>2026-06-02T08:08:30.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conformal-prediction-on-fashionmnist-test</loc><lastmod>2026-06-02T06:45:33.691Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-reasoning-on-frames</loc><lastmod>2026-07-02T08:11:11.431Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-numerical-reasoning-on-finqa-test</loc><lastmod>2026-06-11T10:02:59.800Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temperature-forecasting-on-ersst-test</loc><lastmod>2026-06-01T07:44:20.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temperature-forecasting-on-cesm2-test</loc><lastmod>2026-06-01T07:44:20.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-greedy-pass-at-8</loc><lastmod>2026-05-29T11:51:49.468Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-average-accuracy</loc><lastmod>2026-05-29T08:45:45.870Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-on-countdown-accuracy-and-average-accuracy</loc><lastmod>2026-05-29T08:45:45.824Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/targeted-error-generation-on-theoremqa-tier-1-first-20-sweep</loc><lastmod>2026-05-29T07:42:46.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-label-classification-on-coco-stuff-27</loc><lastmod>2026-05-28T10:42:32.231Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lipschitz-constant-estimation-on-california-housing</loc><lastmod>2026-05-28T10:32:28.940Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-hallucination-detection-on-pope-popular</loc><lastmod>2026-06-29T06:38:47.898Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-sciknoweval-chemistry</loc><lastmod>2026-06-30T10:37:29.971Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/move-prediction-on-lif</loc><lastmod>2026-05-28T08:01:39.423Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/move-prediction-on-lob-c</loc><lastmod>2026-05-28T08:01:39.340Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-gc10-det</loc><lastmod>2026-05-27T07:32:08.225Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-gc10-mini</loc><lastmod>2026-05-27T07:32:08.075Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-steel-pipe</loc><lastmod>2026-05-27T07:32:08.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-casting-billet</loc><lastmod>2026-05-27T07:32:07.979Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-level-anomaly-detection-on-mutag-auroc-auprc-fpr95</loc><lastmod>2026-05-27T07:27:31.950Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-dtd-top-1-clean-and-robust-accuracy</loc><lastmod>2026-06-23T12:17:51.294Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-aircraft-acc-rob</loc><lastmod>2026-06-23T12:17:51.025Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-mmlu-pro-accuracy-and-cost-evaluation</loc><lastmod>2026-06-30T07:31:39.336Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-medical-image-segmentation-on-la-8-labeled-72-unlabeled</loc><lastmod>2026-05-26T11:33:10.768Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-medical-image-segmentation-on-la-20-percent-labeled</loc><lastmod>2026-05-26T11:33:10.631Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/textual-adversarial-attack-on-ag-news</loc><lastmod>2026-05-26T09:39:21.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-information-extraction-on-eppc</loc><lastmod>2026-05-26T07:40:55.636Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-lambada-ppl</loc><lastmod>2026-06-04T09:59:03.850Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-on-cifar-10-c-test</loc><lastmod>2026-05-25T08:30:13.398Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/heart-rate-estimation-on-ubfc-cross-dataset-from-pure-test</loc><lastmod>2026-07-01T08:27:08.426Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-question-answering-on-hotpotqa-test</loc><lastmod>2026-06-11T09:12:54.631Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategy-prediction-on-tom-bpd-test</loc><lastmod>2026-05-22T09:27:10.779Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/belief-prediction-on-tom-bpd-test</loc><lastmod>2026-05-22T09:27:10.740Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/desire-prediction-on-tom-bpd-test</loc><lastmod>2026-05-22T09:27:10.704Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continual-learning-on-x-tail</loc><lastmod>2026-05-28T07:21:11.276Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/composed-image-retrieval-on-genecis-full-r-at-k-specialized-metrics</loc><lastmod>2026-05-21T13:05:35.661Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/odometry-on-graco-aerial-01-to-aerial-08</loc><lastmod>2026-05-21T12:55:32.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-miou-gflops-fps</loc><lastmod>2026-05-21T12:25:20.875Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-error-correction-on-common-voice-frisian-test</loc><lastmod>2026-05-20T09:07:04.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-error-correction-on-frisian-offline-data-test</loc><lastmod>2026-05-20T09:07:04.696Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-error-step-detection-on-morehopqa</loc><lastmod>2026-05-20T07:43:44.615Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-confidence-attribution-on-math</loc><lastmod>2026-05-20T07:43:44.579Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-confidence-attribution-on-morehopqa</loc><lastmod>2026-05-20T07:43:44.545Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-confidence-attribution-on-gsm8k</loc><lastmod>2026-05-20T07:43:44.513Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-sql-on-spider-2-0-test</loc><lastmod>2026-05-20T06:46:47.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-aligned-retrieval-augmented-generation-on-prefeval</loc><lastmod>2026-05-19T12:52:59.721Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-aligned-retrieval-augmented-generation-on-prefeli5</loc><lastmod>2026-05-19T12:52:59.682Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-aligned-retrieval-augmented-generation-on-prefrq</loc><lastmod>2026-05-19T12:52:59.645Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-aligned-retrieval-augmented-generation-on-prefwiki</loc><lastmod>2026-05-19T12:52:59.610Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pansharpening-on-wv3-full-resolution</loc><lastmod>2026-06-17T07:28:58.055Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hate-speech-detection-on-hatexplain</loc><lastmod>2026-05-19T12:18:12.900Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/end-to-end-gp-fit-plus-predict-on-synthetic-gp-data-d-4</loc><lastmod>2026-05-19T11:47:53.936Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-evaluation-on-general-language-evaluation-suite-test</loc><lastmod>2026-05-19T11:38:18.304Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-d-acc-tr</loc><lastmod>2026-05-19T11:14:04.098Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-acc-tr</loc><lastmod>2026-05-19T11:14:04.057Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-acc-tr</loc><lastmod>2026-05-19T11:14:04.018Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-acc-tr</loc><lastmod>2026-05-19T11:14:03.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polynomial-multiplication-on-fq-x-x-n-plus-1</loc><lastmod>2026-05-19T10:52:22.119Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-image-animation-on-realisdance-val</loc><lastmod>2026-06-30T10:41:31.505Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-supergpqa-accuracy</loc><lastmod>2026-06-09T10:08:38.756Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/goal-conditioned-visual-planning-on-crosstask-t-3-88</loc><lastmod>2026-05-19T08:31:36.768Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/motion-prediction-on-round-d1</loc><lastmod>2026-05-19T08:05:53.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/blackbox-optimization-on-ackley-levy-and-rastrigin-functions-test</loc><lastmod>2026-05-19T07:34:33.620Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/customer-segmentation-on-b2b-customer-dataset</loc><lastmod>2026-05-19T06:18:37.476Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-retrieval-on-mirflickr-25k-test</loc><lastmod>2026-05-18T07:17:47.606Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/controllable-molecular-generation-on-molecular-and-polymer-properties-9-properties-aggregation-test</loc><lastmod>2026-05-18T07:07:43.583Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-manipulation-on-robotwin-50-task-seen-tasks</loc><lastmod>2026-07-09T06:29:35.072Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-injection-and-jailbreak-detection-on-ward-test</loc><lastmod>2026-05-15T09:47:18.800Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/e-commerce-product-search-and-purchase-on-webshop</loc><lastmod>2026-07-01T08:44:48.364Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-video-understanding-on-videomme-v1-test</loc><lastmod>2026-05-15T08:03:49.157Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-grounding-on-mot17-test</loc><lastmod>2026-05-15T07:16:25.909Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-grounding-on-ovis-test</loc><lastmod>2026-05-15T07:16:25.832Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-time-series-forecasting-on-electricity-mse-mae</loc><lastmod>2026-06-26T07:50:45.183Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/super-resolution-x2-on-rsscn7</loc><lastmod>2026-05-14T09:56:03.331Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-motion-generation-on-humanml3d-test</loc><lastmod>2026-05-27T09:03:46.809Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-model-1</loc><lastmod>2026-05-14T09:05:46.760Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-sensing-on-gesture-atr-ratio</loc><lastmod>2026-05-14T08:35:36.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-sensing-on-hhar-atr-ratio</loc><lastmod>2026-05-14T08:35:36.378Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/abnormality-detection-on-tuab</loc><lastmod>2026-05-15T06:32:25.028Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-financial-question-answering-on-finvqa-multimodal</loc><lastmod>2026-05-14T06:14:54.274Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-question-answering-on-finvqa-text-only-test</loc><lastmod>2026-05-14T06:14:54.228Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-task-completion-on-libero-success-rate-and-wall-clock-time</loc><lastmod>2026-06-23T09:13:48.218Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-mvtec-ad-i-auc-p-auc-pixel-f1</loc><lastmod>2026-07-03T07:59:36.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lifelong-model-editing-on-fever</loc><lastmod>2026-05-13T09:44:16.830Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-recognition-on-ucf101-train-test</loc><lastmod>2026-05-13T08:03:44.710Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/truthfulness-evaluation-on-truthfulqa-avg-at-k-pass-at-k</loc><lastmod>2026-05-13T07:03:26.231Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ifeval-avg-at-k-pass-at-k</loc><lastmod>2026-05-13T07:03:26.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pixel-level-anomaly-localization-on-brats</loc><lastmod>2026-05-12T16:18:09.661Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pixel-level-anomaly-localization-on-resc</loc><lastmod>2026-05-12T16:18:09.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pixel-level-anomaly-localization-on-mpdd</loc><lastmod>2026-05-12T16:18:09.586Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-problem-solving-on-amc-2023-accuracy-avg-at-k</loc><lastmod>2026-06-23T11:05:58.762Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-pubmed-1-shot</loc><lastmod>2026-06-04T08:44:16.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-1-shot-accuracy</loc><lastmod>2026-06-04T08:44:16.429Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-citeseer-1-shot</loc><lastmod>2026-06-04T08:44:16.400Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-grounding-on-blink</loc><lastmod>2026-05-20T09:37:57.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-2wikimultihopqa-ood</loc><lastmod>2026-05-12T13:42:17.772Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-musique-ood</loc><lastmod>2026-05-12T13:42:17.741Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-hotpotqa-length-and-degeneration-metrics</loc><lastmod>2026-05-12T13:42:17.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-2wikimultihopqa-ood</loc><lastmod>2026-05-12T13:42:17.680Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-musique-ood</loc><lastmod>2026-05-12T13:42:17.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-em-f1-llm</loc><lastmod>2026-05-12T13:42:17.614Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-slr-bench-test</loc><lastmod>2026-05-12T13:15:27.392Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-gpqa-accuracy-multi-choice</loc><lastmod>2026-05-12T12:52:01.146Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-reasoning-on-videomathqa-mcq</loc><lastmod>2026-05-12T12:43:08.107Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-reasoning-on-videommmu-comprehension</loc><lastmod>2026-05-12T12:43:08.068Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-reasoning-on-videommmu-adaptation</loc><lastmod>2026-05-12T12:43:08.029Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-reasoning-on-mmmu-pro-vision</loc><lastmod>2026-05-12T12:43:07.992Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-reasoning-on-mathvision-mini</loc><lastmod>2026-05-12T12:43:07.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-reasoning-on-mmstar</loc><lastmod>2026-05-12T12:43:07.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/neural-super-resolution-for-mesh-based-simulations-on-dataset-3</loc><lastmod>2026-05-12T11:37:20.777Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/neural-super-resolution-for-mesh-based-simulations-on-dataset-2</loc><lastmod>2026-05-12T11:37:20.742Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/neural-super-resolution-for-mesh-based-simulations-on-dataset-1</loc><lastmod>2026-05-12T11:37:20.706Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/creative-storytelling-on-creative-storytelling-prompts</loc><lastmod>2026-05-12T10:59:25.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-test-pass-at-4-avg-at-4</loc><lastmod>2026-05-12T09:52:42.306Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/icd-10-coding-on-mimic-iv-top-50-codes-test</loc><lastmod>2026-06-15T07:01:12.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-dpg-bench-dpg-bench-metric</loc><lastmod>2026-06-11T09:20:57.305Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-problem-solving-on-frontierscience-olympiad</loc><lastmod>2026-05-11T10:02:03.584Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pde-solving-on-darcy-flow-64x64-resolution</loc><lastmod>2026-05-11T09:07:23.070Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pruning-on-cifar-100-test</loc><lastmod>2026-05-11T08:10:47.394Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-grasping-on-intentgrasp-all-set-downsample</loc><lastmod>2026-05-11T07:31:28.604Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-100-coarse-test</loc><lastmod>2026-06-25T08:15:04.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-classification-trajectory-vs-cluster-like-on-single-cell-graphs-gold-subset</loc><lastmod>2026-05-08T11:16:37.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-forecasting-on-metr-la-horizon-12</loc><lastmod>2026-05-27T07:24:31.225Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-em-and-latency</loc><lastmod>2026-05-08T10:42:46.681Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-popqa-em-percent-and-latency</loc><lastmod>2026-05-08T10:42:46.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-percent-lat-ms</loc><lastmod>2026-05-08T10:42:46.604Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-em-and-latency</loc><lastmod>2026-05-08T10:42:46.563Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-retrieval-on-transformed-query-conditions-excluding-clean-prompts-average</loc><lastmod>2026-05-08T08:39:50.796Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-plus-pass-at-1-avg</loc><lastmod>2026-06-11T07:04:01.610Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar20-average-d0-d3</loc><lastmod>2026-05-07T07:16:33.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar20-domain-d3</loc><lastmod>2026-05-07T07:16:33.198Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar20-domain-d2</loc><lastmod>2026-05-07T07:16:33.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar20-domain-d1</loc><lastmod>2026-05-07T07:16:33.098Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar20-domain-d0</loc><lastmod>2026-05-07T07:16:33.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-scenario-generation-on-waymo-open-motion-dataset</loc><lastmod>2026-05-06T07:35:12.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-error-analysis-on-agent-eval-8-templates-user-agent-gpt-5-4-nano-aggregate</loc><lastmod>2026-05-06T07:16:41.755Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-recognition-on-pacs</loc><lastmod>2026-05-26T10:37:39.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-inversion-on-cifar-100</loc><lastmod>2026-07-07T09:43:19.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-b-t2-x-d-50</loc><lastmod>2026-04-30T08:03:56.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-b-t2-x-d-20</loc><lastmod>2026-04-30T08:03:56.327Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-b-t2-x-d-10</loc><lastmod>2026-04-30T08:03:56.289Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-a-t1-x-x-d-50-n-m-5000-test</loc><lastmod>2026-04-30T08:03:56.109Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-a-t1-x-x-d-20-n-m-5000-test</loc><lastmod>2026-04-30T08:03:56.021Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-a-t1-x-x-d-10-n-m-5000-test</loc><lastmod>2026-04-30T08:03:55.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-t3-x-n-5000-d-50-c-test</loc><lastmod>2026-04-30T08:03:55.913Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-t3-x-n-5000-d-20-c-test</loc><lastmod>2026-04-30T08:03:55.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-transport-map-estimation-on-ot-map-t3-x-n-5000-d-10-c-test</loc><lastmod>2026-04-30T08:03:55.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-biomedical-healthcare-datasets-avg</loc><lastmod>2026-04-30T06:32:18.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-question-answering-on-mmlu</loc><lastmod>2026-04-30T06:32:18.351Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-scientific-datasets-average</loc><lastmod>2026-04-30T06:32:18.313Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-bookcrossing</loc><lastmod>2026-04-29T08:27:46.432Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-guided-image-editing-on-kris-bench</loc><lastmod>2026-04-29T08:12:05.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-avg-at-5-accuracy</loc><lastmod>2026-04-29T08:09:03.187Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-amc-avg-at-8-accuracy</loc><lastmod>2026-04-29T08:09:03.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-aime-2025-avg-at-16-accuracy</loc><lastmod>2026-04-29T08:09:03.109Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-aime-2024-avg-at-16-accuracy</loc><lastmod>2026-04-29T08:09:03.074Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-amc-pass-at-8-average</loc><lastmod>2026-04-29T08:09:02.997Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-math-500-pass-at-4-average</loc><lastmod>2026-04-29T08:09:02.878Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-aime25-pass-at-16-average</loc><lastmod>2026-04-29T08:09:02.833Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-aime-24-pass-at-16-average</loc><lastmod>2026-04-29T08:09:02.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-interaction-on-osworld</loc><lastmod>2026-06-15T07:14:25.742Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-language-understanding-mcq-on-mmau-pro-1-0-test</loc><lastmod>2026-04-28T10:21:24.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-language-reasoning-on-mmar-1-0-test</loc><lastmod>2026-04-28T10:21:24.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-language-understanding-on-mmau-1-0-test</loc><lastmod>2026-04-28T10:21:24.811Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/secondary-risk-discovery-on-excessive-response</loc><lastmod>2026-04-28T09:50:59.196Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-svamp-pass-at-1-accuracy</loc><lastmod>2026-06-11T07:09:35.195Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-blink</loc><lastmod>2026-05-21T10:29:22.906Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-2wikimultihopqa-em-only</loc><lastmod>2026-05-22T09:17:35.361Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-skywork-reward-preference-test</loc><lastmod>2026-04-28T07:20:16.656Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-classification-on-mvtec-ad-auroc-f1-ap</loc><lastmod>2026-05-18T09:19:18.355Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/iris-verification-on-immeriris-dual-1-0</loc><lastmod>2026-04-28T06:50:04.804Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-x-en-on-multilingual-intersection-medium-resource</loc><lastmod>2026-04-27T06:32:28.420Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-en-x-on-multilingual-intersection-medium-resource</loc><lastmod>2026-04-27T06:32:28.383Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-x-en-on-multilingual-intersection-high-resource</loc><lastmod>2026-04-27T06:32:28.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-en-x-on-multilingual-intersection-high-resource</loc><lastmod>2026-04-27T06:32:28.247Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-medium-resource</loc><lastmod>2026-04-27T06:32:27.783Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-high-resource-bleu-directions</loc><lastmod>2026-04-27T06:32:27.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-val-gflops-miou</loc><lastmod>2026-04-24T06:58:36.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-adni-clinical-tabular-dataset</loc><lastmod>2026-04-23T10:12:53.224Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-cme-clinical-tabular</loc><lastmod>2026-04-23T10:12:53.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-airbnb-listings</loc><lastmod>2026-04-23T10:12:53.113Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-retrieval-on-ott-qa-test</loc><lastmod>2026-05-19T12:44:11.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/slot-filling-on-etid</loc><lastmod>2026-04-23T09:22:22.044Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-language-evaluation-on-wikitext2-boolq-piqa-hellaswag-winogrande-arc-obqa-and-mtqa-test</loc><lastmod>2026-04-23T08:52:04.185Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/brain-region-segmentation-on-fthp</loc><lastmod>2026-04-23T08:49:02.466Z</lastmod></url></urlset>