<?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/localization-on-carpark-long-term-test</loc><lastmod>2026-06-25T08:41:20.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/incremental-image-classification-on-imagenet-100-test-from-scratch</loc><lastmod>2026-06-25T08:13:02.978Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extreme-multi-label-classification-on-lf-wikipedia-500k-10</loc><lastmod>2026-06-25T08:03:54.044Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extreme-multi-label-classification-on-lf-wikihierarchy-550k-10</loc><lastmod>2026-06-25T08:03:54.003Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extreme-multi-label-classification-on-lf-aol-270k-10</loc><lastmod>2026-06-25T08:03:53.961Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prediction-under-missing-values-on-life-test</loc><lastmod>2026-06-25T07:51:44.194Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/field-reconstruction-on-vallecas-dataset-two-building-t-224</loc><lastmod>2026-06-25T07:39:35.747Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/creative-writing-on-ab-w</loc><lastmod>2026-06-25T07:42:39.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/camera-relocalization-on-scannet-plus-plus-val</loc><lastmod>2026-06-24T08:51:58.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-finheadlinemix</loc><lastmod>2026-06-24T08:48:56.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-snapshot-compressive-imaging-reconstruction-on-traffic</loc><lastmod>2026-06-24T07:50:36.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-snapshot-compressive-imaging-reconstruction-on-runner</loc><lastmod>2026-06-24T07:50:36.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-retrieval-accuracy-on-ruler-test</loc><lastmod>2026-06-24T07:31:52.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dynamical-system-prediction-on-irma</loc><lastmod>2026-06-24T07:30:51.953Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dynamical-system-prediction-on-repressilator</loc><lastmod>2026-06-24T07:30:51.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dynamical-system-prediction-on-duffing-oscillator</loc><lastmod>2026-06-24T07:30:51.882Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-cambrian-benchmarks</loc><lastmod>2026-06-24T07:27:19.559Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-discovery-on-scp-sparse-test</loc><lastmod>2026-06-24T07:26:49.239Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-overall-gsm8k-math-500-amc-2023-aime-2024-aime-2025</loc><lastmod>2026-06-24T07:07:37.074Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-accuracy-tokens</loc><lastmod>2026-06-24T07:07:37.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-audio-diagnosis-on-clinical-audio-diagnosis-14-respiratory-and-cardiac-categories-test</loc><lastmod>2026-06-23T12:24:56.167Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-continual-learning-task-stream-s</loc><lastmod>2026-06-23T12:05:42.187Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/training-optimization-efficiency-on-h200-performance-sweep</loc><lastmod>2026-06-23T11:58:37.528Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-text-synthesis-on-loan</loc><lastmod>2026-06-23T11:45:27.045Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-text-synthesis-on-mimic</loc><lastmod>2026-06-23T11:45:27.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-text-synthesis-on-water</loc><lastmod>2026-06-23T11:45:26.960Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermark-detection-on-tracemark-ldm-test</loc><lastmod>2026-06-23T11:29:44.276Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pulmonary-nodule-segmentation-on-multi-center-n-134-test</loc><lastmod>2026-06-23T10:56:51.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-uci-har-5-class-test</loc><lastmod>2026-06-23T10:51:48.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-5-class-subset-test</loc><lastmod>2026-06-23T10:51:48.259Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mnist-7-class</loc><lastmod>2026-06-23T10:51:48.229Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-7-class</loc><lastmod>2026-06-23T10:51:48.200Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-uci-har-6classes</loc><lastmod>2026-06-23T10:51:48.167Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mnist-6classes</loc><lastmod>2026-06-23T10:51:48.130Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-6classes-accuracy</loc><lastmod>2026-06-23T10:51:48.094Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-uci-har-3-class</loc><lastmod>2026-06-23T10:51:48.063Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mnist-3-class</loc><lastmod>2026-06-23T10:51:48.004Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-3-class-accuracy</loc><lastmod>2026-06-23T10:51:47.954Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mnist-8classes</loc><lastmod>2026-06-23T10:51:47.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-8classes-accuracy</loc><lastmod>2026-06-23T10:51:47.876Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-uci-har-4-class</loc><lastmod>2026-06-23T10:51:47.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mnist-4-class</loc><lastmod>2026-06-23T10:51:47.630Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-4-class-accuracy</loc><lastmod>2026-06-23T10:51:47.593Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mnist-9classes</loc><lastmod>2026-06-23T10:51:47.552Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-isolet-9classes-accuracy</loc><lastmod>2026-06-23T10:51:47.509Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-attribution-on-mini-imagenet-500-randomly-sampled-images-val</loc><lastmod>2026-06-23T10:41:10.638Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-attribution-on-oxford-iiit-pet-full-val</loc><lastmod>2026-06-23T10:41:10.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar100-10-split</loc><lastmod>2026-06-23T10:20:27.823Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-alignment-on-cora</loc><lastmod>2026-06-23T10:19:27.358Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-alignment-on-arena</loc><lastmod>2026-06-23T10:19:27.325Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-alignment-on-celegans-matching-accuracy</loc><lastmod>2026-06-23T10:19:27.290Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-flow-prediction-on-pems03-test</loc><lastmod>2026-06-23T10:14:55.063Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-gsm8k-aime-24-amc-23-olympiadbench-and-minerva-math-test</loc><lastmod>2026-06-23T10:14:55.023Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/in-hand-reorientation-on-ycb-1-0-test</loc><lastmod>2026-06-23T09:37:32.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-real-world-translation-benchmarks-ja-en</loc><lastmod>2026-06-23T09:07:13.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-diversity-optimisation-on-a280-tsplib-1-0-test</loc><lastmod>2026-06-23T08:14:41.369Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-diversity-optimisation-on-tsplib-eil101-1-0-test</loc><lastmod>2026-06-23T08:14:41.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-diversity-optimisation-on-tsplib-st70-1-0-test</loc><lastmod>2026-06-23T08:14:41.298Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pose-estimation-on-forest-environment-simulation-various-difficulties-easy-medium-hard</loc><lastmod>2026-06-23T07:34:08.704Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-agent-attack-on-seeact</loc><lastmod>2026-06-23T07:34:07.390Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-cktbench</loc><lastmod>2026-06-23T07:25:08.055Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spreadsheet-reasoning-on-spreadsheetbench-test</loc><lastmod>2026-06-19T08:48:36.108Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-decision-making-on-alfworld-test</loc><lastmod>2026-06-19T08:48:36.064Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-ca-and-asr-evaluation</loc><lastmod>2026-06-19T08:33:42.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-defense-on-tiny-imagenet-ca-asr</loc><lastmod>2026-06-19T08:33:42.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-object-detection-on-kitti-train</loc><lastmod>2026-06-19T08:27:15.442Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-csqa-acc-length</loc><lastmod>2026-06-30T06:45:18.568Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/algebraic-word-problems-on-aqua-accuracy</loc><lastmod>2026-06-19T07:43:21.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-153-question-shuffled-subset</loc><lastmod>2026-06-19T07:43:21.402Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-simulation-on-scienceworld</loc><lastmod>2026-06-19T07:23:12.161Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/session-based-recommendation-on-retailrocket-hr-mrr-tail-k-20</loc><lastmod>2026-06-19T06:53:01.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/session-based-recommendation-on-tmall-hr-mrr-tail-at-20</loc><lastmod>2026-06-19T06:53:01.340Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hate-speech-detection-on-ihc</loc><lastmod>2026-06-18T08:15:30.994Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hate-speech-detection-on-dynahate</loc><lastmod>2026-06-18T08:15:30.951Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/skilled-forgery-detection-on-cedar</loc><lastmod>2026-06-18T07:32:17.828Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/skilled-forgery-detection-on-gpds-s</loc><lastmod>2026-06-18T07:32:17.786Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/downscaling-on-weatherbench-era5-5-625-to-1-40625</loc><lastmod>2026-06-18T07:22:13.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-topic-and-sentiment-classification-on-sib-200-and-sentiment-collection-test</loc><lastmod>2026-06-18T07:02:01.928Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decoder-reconstruction-on-gemma-4b-it-3</loc><lastmod>2026-06-18T06:52:03.946Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multitask-language-understanding-on-mmlu-mmlu-score-average</loc><lastmod>2026-06-18T06:51:59.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-segmentation-on-cubicasa</loc><lastmod>2026-06-18T06:41:57.335Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/world-modelling-on-alfworld</loc><lastmod>2026-06-17T08:11:51.080Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/countdown-on-countdown-5</loc><lastmod>2026-06-17T07:53:55.912Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-reasoning-on-hotpotqa-accuracy-f1</loc><lastmod>2026-06-17T07:06:11.039Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm-hard-acc-pass-at-5</loc><lastmod>2026-06-17T07:06:11.000Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-acc-pass-at-5</loc><lastmod>2026-06-17T07:06:10.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/success-rate-estimation-on-robomme-stopcube</loc><lastmod>2026-06-17T07:01:20.368Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-discovery-on-lorenz-96-d-40-t-1000</loc><lastmod>2026-06-17T06:31:05.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-adversarial-attack-on-kinetics-400</loc><lastmod>2026-06-17T06:22:45.653Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-adversarial-attack-on-hmdb-51</loc><lastmod>2026-06-17T06:22:45.611Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-research-report-generation-on-drb</loc><lastmod>2026-06-16T11:13:23.506Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-vocabulary-semantic-segmentation-on-pascal-voc-2012-v20</loc><lastmod>2026-06-16T11:10:21.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/profession-prediction-on-bias-in-bios-bib-balanced-test</loc><lastmod>2026-06-16T11:01:15.730Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pde-solving-on-heat-pde</loc><lastmod>2026-06-16T10:36:30.688Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pde-solving-on-diffusion-pde-error-metrics</loc><lastmod>2026-06-16T10:36:30.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-coqa-exact-match</loc><lastmod>2026-06-16T10:14:12.749Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-femnist-natural-partition-test</loc><lastmod>2026-06-16T09:50:17.851Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-cifar-100-alpha_dir-0-5-test</loc><lastmod>2026-06-16T09:50:17.817Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-cifar-10-alpha_dir-0-5-test</loc><lastmod>2026-06-16T09:50:17.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-temporal-classification-on-uci-har-test</loc><lastmod>2026-06-16T09:24:03.275Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-temporal-classification-on-mhealth-test</loc><lastmod>2026-06-16T09:24:03.232Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-temporal-classification-on-harth-test</loc><lastmod>2026-06-16T09:24:03.192Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-temporal-classification-on-ptb-xl-test</loc><lastmod>2026-06-16T09:24:03.146Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/blind-source-separation-on-cmu-arctic-noisy-condition-snr-uniformly-sampled-from-15-25-db</loc><lastmod>2026-06-16T08:51:42.584Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/blind-source-separation-on-cmu-arctic-noiseless-condition-snr</loc><lastmod>2026-06-16T08:51:42.528Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-yelp-hr-ndcg-at-10-20</loc><lastmod>2026-06-18T08:19:03.792Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-arxiv-real-world</loc><lastmod>2026-06-16T08:35:58.179Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-pubmed-real-world-accuracy</loc><lastmod>2026-06-16T08:35:58.142Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-real-world-accuracy</loc><lastmod>2026-06-16T08:35:58.104Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-held-out-pass-at-1</loc><lastmod>2026-06-16T11:12:53.126Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/whole-slide-image-classification-on-bcnb</loc><lastmod>2026-06-16T08:29:42.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/whole-slide-image-classification-on-in-house</loc><lastmod>2026-06-16T08:29:42.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-and-scientific-reasoning-on-average-gsm8k-math-500-aime-2024-olympiadbench-gpqa-diamond</loc><lastmod>2026-06-16T07:12:56.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-diamond-acc-len-cr</loc><lastmod>2026-06-16T07:12:56.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-acc-len-cr</loc><lastmod>2026-06-16T07:12:56.618Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-accuracy-length-cr</loc><lastmod>2026-06-16T07:12:56.576Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-acc-len-cr</loc><lastmod>2026-06-16T07:12:56.538Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-cifar-10-ari</loc><lastmod>2026-06-16T06:38:57.978Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/6d-object-pose-estimation-on-lm-o</loc><lastmod>2026-06-15T07:48:42.635Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/6d-object-pose-estimation-on-ycb-v-auc-and-ar</loc><lastmod>2026-06-15T07:48:42.552Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-question-answering-and-instruction-following-on-dolly</loc><lastmod>2026-06-15T07:28:33.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medicalmeadow-wikidoc-patientinfo-med</loc><lastmod>2026-06-15T07:28:33.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/finance-question-answering-on-financial-qa-10k</loc><lastmod>2026-06-15T07:28:33.710Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-leakage-attack-on-dolly</loc><lastmod>2026-06-15T07:28:33.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-leakage-attack-on-med</loc><lastmod>2026-06-15T07:28:33.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-leakage-attack-on-fin</loc><lastmod>2026-06-15T07:28:33.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-yelp-recall-at-50-ndcg-at-50-recall-at-100-ndcg-at-100</loc><lastmod>2026-06-15T07:10:22.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-amazon-book-recall-at-50-recall-at-100</loc><lastmod>2026-06-15T07:10:22.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-movielens-recall-at-50-ndcg-at-50-recall-at-100-ndcg-at-100</loc><lastmod>2026-06-15T07:10:22.047Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-similarity-on-mrpc-test</loc><lastmod>2026-06-15T06:44:29.785Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-test-accuracy-and-normalized-accuracy</loc><lastmod>2026-06-15T06:44:29.736Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-domain-evaluation-on-diverse-domain-collection-math-gsm-h-aqua-aime-scibe-gpqa-mmlup-medmc-heval-mbpp</loc><lastmod>2026-06-15T06:28:07.784Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-on-scibench-accuracy</loc><lastmod>2026-06-15T06:28:07.734Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimal-subgroup-identification-on-eicu-ventilation-free-days-within-7-days-test</loc><lastmod>2026-06-15T06:28:07.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/subgroup-identification-on-eicu-ventilation-free-days-outcome</loc><lastmod>2026-06-15T06:28:07.191Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-medqa-accuracy-tflops</loc><lastmod>2026-06-12T08:21:32.572Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-arc-challenge-accuracy-tflops</loc><lastmod>2026-06-12T08:21:32.523Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overall-spreadsheet-performance-on-spreadsheetbench-and-wikitablequestions-combined</loc><lastmod>2026-06-12T07:58:42.566Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/out-of-distribution-table-question-answering-on-wikitablequestions-wikitq</loc><lastmod>2026-06-12T07:58:42.518Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spreadsheet-task-execution-on-spreadsheetbench-full</loc><lastmod>2026-06-12T07:58:42.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spreadsheet-task-execution-on-spreadsheetbench-verified-held-out</loc><lastmod>2026-06-12T07:58:42.417Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-covid-19-79-regions</loc><lastmod>2026-06-12T07:53:38.172Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/equilibrium-state-estimation-on-covid-19-test</loc><lastmod>2026-06-12T07:53:37.308Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bilingual-response-generation-on-chinese-zh</loc><lastmod>2026-06-12T07:49:02.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bilingual-response-generation-on-english-en</loc><lastmod>2026-06-12T07:49:02.433Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pick-toy-on-real-world-robot-experiments-v1-test</loc><lastmod>2026-06-12T07:07:28.557Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intrusion-detection-on-bot-iot-test</loc><lastmod>2026-06-12T07:07:19.841Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continual-learning-on-split-cifar-10</loc><lastmod>2026-06-23T10:14:24.224Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multicalibration-on-bank-marketing</loc><lastmod>2026-06-12T06:49:46.474Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-accuracy-rejection-rate</loc><lastmod>2026-06-11T11:16:53.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-video-understanding-on-longvideobench-duration-specific-metrics</loc><lastmod>2026-06-11T11:06:50.769Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rollout-prediction-on-cahn-hilliard-3d-accuracy-and-timing</loc><lastmod>2026-06-11T10:56:43.618Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rollout-prediction-on-swift-hohenberg-3d-test</loc><lastmod>2026-06-11T10:56:43.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pde-rollout-on-allen-cahn-3d-accuracy-and-timing</loc><lastmod>2026-06-11T10:56:43.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/label-correction-on-yahoo-answer</loc><lastmod>2026-06-11T10:26:32.117Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-classification-on-diabetes-auc</loc><lastmod>2026-06-11T10:16:28.459Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-classification-on-amazon</loc><lastmod>2026-06-11T10:16:28.416Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-classification-on-adult-auc</loc><lastmod>2026-06-11T10:16:28.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/suturing-on-suturing</loc><lastmod>2026-06-11T10:06:22.154Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/surgical-debridement-on-debridement-subtask</loc><lastmod>2026-06-11T10:06:22.117Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-halfcheetah-extreme-env-v2-various</loc><lastmod>2026-06-11T09:31:03.484Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-halfcheetah-random-env-v2-various</loc><lastmod>2026-06-11T09:31:03.449Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-halfcheetah-standard-env-v2-various</loc><lastmod>2026-06-11T09:31:03.406Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-on-nuplan-test14</loc><lastmod>2026-06-11T08:55:52.656Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sycophancy-evaluation-on-mist-moral</loc><lastmod>2026-06-11T08:50:01.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sycophancy-evaluation-on-mist-science</loc><lastmod>2026-06-11T08:50:01.757Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-classification-on-starkey-dataset</loc><lastmod>2026-06-11T08:49:01.057Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-classification-on-foxes-dataset</loc><lastmod>2026-06-11T08:49:01.020Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-classification-on-car-traffic-dataset</loc><lastmod>2026-06-11T08:49:00.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-classification-on-ais-subset</loc><lastmod>2026-06-11T08:49:00.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-document-style-memory-reasoning-on-musique</loc><lastmod>2026-06-11T08:26:43.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-document-style-memory-reasoning-on-2wikimultihopqa-em-lj</loc><lastmod>2026-06-11T08:26:42.965Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-document-style-memory-reasoning-on-hotpotqa</loc><lastmod>2026-06-11T08:26:42.929Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-style-memory-reasoning-on-personamem</loc><lastmod>2026-06-11T08:26:42.891Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-style-memory-reasoning-on-longmemeval</loc><lastmod>2026-06-11T08:26:42.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-style-memory-reasoning-on-locomo-metrics-em-lj</loc><lastmod>2026-06-11T08:26:42.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-task-capability-preservation-on-qwen-image</loc><lastmod>2026-06-11T08:15:31.468Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quadrotor-motion-planning-on-quadrotor-motion-planning-variational-integrator</loc><lastmod>2026-06-11T08:05:28.525Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-average-nq-tabmwp-hotpotqa-triviaqa-tristate</loc><lastmod>2026-06-11T07:25:13.740Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-tristate</loc><lastmod>2026-06-11T07:25:13.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-natural-questions-nq-em-f1-metrics</loc><lastmod>2026-06-11T07:25:13.665Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-tristate-bench</loc><lastmod>2026-06-11T07:25:13.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/context-aware-generation-on-tristate-bench-agreement-sagr-gold-context-prior-correct</loc><lastmod>2026-06-11T07:25:13.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/context-aware-generation-on-tristate-bench-resistance-corrupted-context-prior-correct-sres</loc><lastmod>2026-06-11T07:25:13.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/context-aware-generation-on-tristate-bench-correction-gold-context-prior-incorrect-scor</loc><lastmod>2026-06-11T07:25:13.463Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pde-surrogate-modeling-on-2d-kuramoto-sivashinsky-and-gray-scott</loc><lastmod>2026-06-11T06:57:56.306Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-and-safety-preservation-on-gsm8k</loc><lastmod>2026-06-11T06:44:56.488Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-alignment-and-instruction-following-on-redorca</loc><lastmod>2026-06-11T06:44:56.451Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/attack-and-collusion-detection-monitoring-on-basharena-held-out-80-percent-honest-rollouts</loc><lastmod>2026-06-11T06:24:46.816Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-average-math-oai-minerva-math-olympiadbench-aime24-amc23</loc><lastmod>2026-06-09T10:54:26.309Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-23-avg-at-16-p-at-16</loc><lastmod>2026-06-09T10:54:26.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-avg-at-16-p-at-16</loc><lastmod>2026-06-09T10:54:26.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-avg-at-16-p-at-16</loc><lastmod>2026-06-09T10:54:26.194Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/velocity-estimation-on-simulated-events-synthetic-test</loc><lastmod>2026-06-09T10:24:14.794Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/absolute-pose-estimation-on-simulated-events-synthetic-test</loc><lastmod>2026-06-09T10:24:14.755Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-and-classification-on-mtd</loc><lastmod>2026-06-09T09:35:47.771Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-and-classification-on-mvtec-fs</loc><lastmod>2026-06-09T09:35:47.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-localization-on-wfdd</loc><lastmod>2026-06-09T09:35:47.700Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnostic-endpoint-prediction-on-mmrf-commpass</loc><lastmod>2026-06-09T08:57:16.874Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-naming-evaluation-on-lattice-concepts-trials-14-and-15</loc><lastmod>2026-06-09T08:46:06.668Z</lastmod></url></urlset>