<?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/visual-spatial-reasoning-on-spacevista-bench-overall</loc><lastmod>2026-05-27T07:33:41.821Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-spatial-reasoning-on-spacevista-bench-outdoor</loc><lastmod>2026-05-27T07:33:41.768Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-spatial-reasoning-on-spacevista-bench-indoor</loc><lastmod>2026-05-27T07:33:41.722Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-spatial-reasoning-on-spacevista-bench-tabletop</loc><lastmod>2026-05-27T07:33:41.662Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-time-series-forecasting-on-pems-bay-horizon-12</loc><lastmod>2026-05-27T07:24:30.338Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-paper-review-on-mlrbench</loc><lastmod>2026-05-27T07:00:05.880Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/two-player-asymmetric-strategy-game-playing-on-wargame</loc><lastmod>2026-05-27T07:00:04.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-unconditional-sequences</loc><lastmod>2026-05-26T13:44:00.308Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/secret-word-task</loc><lastmod>2026-05-26T13:37:26.544Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clause-classification-on-gray-clauses</loc><lastmod>2026-05-26T13:34:23.875Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autoregressive-rollout-prediction-on-thewell-asm-steps-21-60-test</loc><lastmod>2026-05-26T13:23:42.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-quality-assessment-on-c4</loc><lastmod>2026-05-26T12:41:48.899Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermark-detection-on-c4-tpr-at-1-percent-fpr</loc><lastmod>2026-05-26T12:41:48.848Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/large-language-model-watermarking-on-booksum-test</loc><lastmod>2026-05-26T12:41:48.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semi-supervised-classification-on-nifd-10-percent-train-90-percent-test</loc><lastmod>2026-05-26T11:52:21.158Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semi-supervised-classification-on-adni-cn-vs-mci-10-percent-train-90-percent-test</loc><lastmod>2026-05-26T11:52:21.126Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semi-supervised-classification-on-medmnist-breast-10-percent-train-90-percent-test</loc><lastmod>2026-05-26T11:52:21.091Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt-nov-25</loc><lastmod>2026-05-26T11:39:21.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-beyond-aime-avg-at-k</loc><lastmod>2026-05-26T11:39:21.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt-feb-25</loc><lastmod>2026-05-26T11:39:21.375Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pde-solving-on-navier-stokes-ns-problem</loc><lastmod>2026-06-09T06:26:27.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/meta-evaluation-of-unlearning-metrics-on-tofu</loc><lastmod>2026-05-26T08:58:33.763Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-boundary-over-refusal-on-orbench</loc><lastmod>2026-05-26T08:49:43.863Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-coauthor-cs-5-way-5-shot</loc><lastmod>2026-05-26T08:28:23.695Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-coauthor-cs-5-way-3-shot</loc><lastmod>2026-05-26T08:28:23.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-coauthor-cs-2-way-5-shot</loc><lastmod>2026-05-26T08:28:23.632Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-coauthor-cs-2-way-3-shot</loc><lastmod>2026-05-26T08:28:23.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-2-way-5-shot-accuracy-percent</loc><lastmod>2026-05-26T08:28:23.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-2-way-3-shot-accuracy-percent</loc><lastmod>2026-05-26T08:28:23.537Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-2-way-1-shot-accuracy</loc><lastmod>2026-05-26T08:28:23.505Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-corafull-10-way-5-shot-accuracy</loc><lastmod>2026-05-26T08:28:23.473Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-corafull-10-way-3-shot-accuracy</loc><lastmod>2026-05-26T08:28:23.447Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-corafull-5-way-5-shot-accuracy</loc><lastmod>2026-05-26T08:28:23.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-bigcodebench-mean-accuracy</loc><lastmod>2026-05-26T08:08:17.345Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-plus-mean-accuracy</loc><lastmod>2026-05-26T08:08:17.308Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-plus-mean-accuracy</loc><lastmod>2026-05-26T08:08:17.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/eigensolving-on-shapenetcore-point-cloud-discretizations-test</loc><lastmod>2026-05-26T07:58:13.884Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-trec-covid</loc><lastmod>2026-05-26T07:51:32.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-scidocs</loc><lastmod>2026-05-26T07:51:32.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-nfcorpus</loc><lastmod>2026-05-26T07:51:32.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ai-generated-image-detection-on-forensynths-v1-test</loc><lastmod>2026-05-26T07:50:30.927Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fake-image-detection-on-diffusion</loc><lastmod>2026-05-26T07:50:30.888Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/android-malware-detection-on-emulator</loc><lastmod>2026-05-26T07:48:09.134Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-scibench-physics</loc><lastmod>2026-05-26T07:42:26.474Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-scibench-chemistry</loc><lastmod>2026-05-26T07:42:26.446Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-analysis-on-databench</loc><lastmod>2026-05-26T07:42:26.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-of-experience-qoe-evaluation-on-orin</loc><lastmod>2026-05-26T07:28:01.210Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-of-experience-qoe-evaluation-on-xavier</loc><lastmod>2026-05-26T07:28:01.184Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-of-experience-qoe-evaluation-on-tx2</loc><lastmod>2026-05-26T07:28:01.158Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-of-experience-qoe-evaluation-on-nano</loc><lastmod>2026-05-26T07:28:01.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adaptive-retrieval-privacy-attack-success-on-500-nearest-neighbor-and-random-prefix-pairs-mid-network-layer</loc><lastmod>2026-05-26T07:28:00.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-and-logical-reasoning-on-csqa-strategyqa-logiqa</loc><lastmod>2026-05-26T07:07:53.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-logiqa-accuracy-improvement</loc><lastmod>2026-05-26T07:07:53.511Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-strategyqa-accuracy-improvement</loc><lastmod>2026-05-26T07:07:53.480Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-csqa-accuracy-and-improvement</loc><lastmod>2026-05-26T07:07:53.444Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-mathqa-accuracy-and-improvement</loc><lastmod>2026-05-26T07:07:53.378Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-svamp-accuracy-improvement</loc><lastmod>2026-05-26T07:07:53.322Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-i2b2-2014-test</loc><lastmod>2026-05-26T06:47:51.216Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/edited-image-captioning-on-mmedit-e-ic</loc><lastmod>2026-05-25T09:07:45.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/edited-visual-question-answering-on-mmedit-e-vqa</loc><lastmod>2026-05-25T09:07:45.086Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-dimensional-optimization-on-limo</loc><lastmod>2026-05-25T08:40:20.327Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-dimensional-optimization-on-lasso-hard</loc><lastmod>2026-05-25T08:40:20.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-writing-on-writingbench</loc><lastmod>2026-06-01T07:27:44.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/weight-space-classification-on-model-jungle-accuracy</loc><lastmod>2026-05-25T08:30:13.275Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-96k</loc><lastmod>2026-05-25T08:19:36.530Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-performance-evaluation-on-locomo-tau-96k-test</loc><lastmod>2026-05-25T08:19:36.496Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-100-ltn-asymmetric-noise-if-10-nr-40-percent-test</loc><lastmod>2026-05-25T08:12:31.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-100-ltn-symmetric-noise-if-10-nr-40-percent-test</loc><lastmod>2026-05-25T08:12:31.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-stl10</loc><lastmod>2026-05-25T08:12:01.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/out-of-distribution-detection-on-cifar-10-in-distribution-vs-svhn-ood-test</loc><lastmod>2026-07-09T07:40:50.113Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-cifar100c-test</loc><lastmod>2026-05-25T08:12:00.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-class-classification-on-cifar100-lt-imbalance-factor-0-1-test</loc><lastmod>2026-05-25T08:12:00.593Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-evaluation-on-imdb</loc><lastmod>2026-05-25T08:10:30.176Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-evaluation-on-edufeedback-alternate</loc><lastmod>2026-05-25T08:10:30.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-evaluation-on-ultrafeedback</loc><lastmod>2026-05-25T08:10:30.112Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-alignment-on-edufeedback</loc><lastmod>2026-05-25T08:10:30.082Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inversion-attack-recovery-on-icliniq</loc><lastmod>2026-05-25T07:57:20.691Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inversion-attack-recovery-on-alpacaeval</loc><lastmod>2026-05-25T07:57:20.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-privacy-evaluation-on-icliniq-test</loc><lastmod>2026-05-25T07:57:20.615Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-privacy-evaluation-on-alpacaeval-test</loc><lastmod>2026-05-25T07:57:20.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/monocular-depth-estimation-on-scannet-100-sequences</loc><lastmod>2026-05-25T07:50:15.597Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-accuracy-average-generated-tokens</loc><lastmod>2026-05-25T07:47:16.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/aircraft-maintenance-task-scheduling-on-boeing-737ng-600-instances</loc><lastmod>2026-05-25T06:27:00.780Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-sequential-communication-on-agentleak</loc><lastmod>2026-05-22T09:53:55.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-mmlu-answer-letter-accuracy</loc><lastmod>2026-05-22T09:36:48.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-codealpaca-20k-nll</loc><lastmod>2026-05-22T09:36:48.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-aesthetic-4k-test</loc><lastmod>2026-05-22T09:36:48.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-problem-solving-on-mmath-test</loc><lastmod>2026-05-22T09:26:44.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-loop-collaborative-driving-on-carla-town05</loc><lastmod>2026-05-22T09:16:42.873Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-question-answering-on-gpqa-main-test</loc><lastmod>2026-05-22T09:16:41.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiad-p-at-1-asrt-ras</loc><lastmod>2026-05-22T09:16:41.143Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-23-p-at-1-asrt-ras</loc><lastmod>2026-05-22T09:16:41.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-minerva-p-at-1-asrt-ras</loc><lastmod>2026-05-22T09:16:41.030Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-p-at-1-asrt-ras</loc><lastmod>2026-05-22T09:16:40.988Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-p-at-1-asrt-ras</loc><lastmod>2026-05-22T09:16:40.951Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generalized-category-discovery-on-cifar10-cifar100-imagenet-100</loc><lastmod>2026-05-22T09:16:40.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/receipt-information-extraction-on-receiptbench-1-0-test</loc><lastmod>2026-05-22T08:56:34.630Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-recognition-on-seed-accuracy</loc><lastmod>2026-06-02T09:30:26.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-gqa-gqa-score-average-and-relative-performance-percent</loc><lastmod>2026-07-01T07:53:21.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/linear-regression-on-santander</loc><lastmod>2026-05-22T08:28:01.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-resolution-perception-on-vstar</loc><lastmod>2026-05-22T08:26:23.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/earth-science-reasoning-on-msearthmcq</loc><lastmod>2026-05-22T08:26:23.876Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/microscopic-reasoning-on-microvqa</loc><lastmod>2026-05-22T08:26:23.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-parsing-on-chartqa</loc><lastmod>2026-05-22T08:26:23.788Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-mathvision-accuracy</loc><lastmod>2026-07-03T07:06:40.317Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mri-reconstruction-on-cc359-brain-2004-test</loc><lastmod>2026-05-22T08:09:15.206Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mri-reconstruction-on-fastmri-knee-2018-test</loc><lastmod>2026-05-22T08:09:15.169Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-grounding-on-mm-conv-full-np-1-0</loc><lastmod>2026-05-22T07:36:26.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/runtime-on-virat-1-0-verification</loc><lastmod>2026-05-22T07:26:03.195Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-visualprocessbench-overall</loc><lastmod>2026-05-22T07:28:50.130Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-mathverse-vo</loc><lastmod>2026-05-22T07:28:50.090Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-mathvision-metrics-fei-aei</loc><lastmod>2026-05-22T07:28:50.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-mmmu-fei-aei</loc><lastmod>2026-05-22T07:28:50.008Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyperspectral-image-super-resolution-on-kennedy-space-center</loc><lastmod>2026-05-22T07:32:23.224Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hyperspectral-image-super-resolution-on-pavia-university-mean-value-of-80-lr-hsi-hr-msi-configurations</loc><lastmod>2026-05-22T07:32:23.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-pass-at-1-pass-at-3</loc><lastmod>2026-05-22T06:55:51.630Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-and-stem-reasoning-on-scibench</loc><lastmod>2026-05-22T06:55:51.580Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-and-stem-reasoning-on-medqa-pass-at-k</loc><lastmod>2026-05-22T06:55:51.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-and-stem-reasoning-on-hle</loc><lastmod>2026-05-22T06:55:51.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-and-stem-reasoning-on-chembench</loc><lastmod>2026-05-22T06:55:51.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-and-stem-reasoning-on-cs-bench</loc><lastmod>2026-05-22T06:55:51.422Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-hle-head-to-head-win-percent</loc><lastmod>2026-05-21T13:15:39.390Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spreadsheet-tasks-on-ssb-spreadsheetbench</loc><lastmod>2026-05-21T13:15:39.245Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/root-estimation-on-fitted-q-regression</loc><lastmod>2026-05-21T13:15:38.846Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anxiety-prediction-on-college-experience-ds3</loc><lastmod>2026-05-21T13:05:36.297Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-weather-ood</loc><lastmod>2026-05-21T12:35:25.162Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-munichcarbon</loc><lastmod>2026-05-21T12:15:19.886Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/guided-flow-matching-on-synthetic-dataset-10k-samples-2-dimensional-mixture-of-gaussians</loc><lastmod>2026-05-21T11:45:11.189Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-classification-on-timecap-weather-finance-and-healthcare-average</loc><lastmod>2026-05-21T10:24:42.347Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-time-dynamics-estimation-on-synthetic-arch-first-snapshot-as-initial-state</loc><lastmod>2026-05-21T10:14:37.249Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-time-dynamics-estimation-on-synthetic-y-shaped-first-snapshot-as-initial-state</loc><lastmod>2026-05-21T10:14:37.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-reasoning-on-spbench-mv</loc><lastmod>2026-06-18T08:52:03.501Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/camera-motion-captioning-on-camerabench</loc><lastmod>2026-05-20T09:54:27.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generative-modeling-on-gumbel-plus-gaussian-median-across-all-configurations-480-values-per-cell</loc><lastmod>2026-05-20T09:44:24.567Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/flow-matching-on-gumbel-plus-gaussian-alpha-2-0</loc><lastmod>2026-05-20T09:44:24.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/flow-matching-on-gumbel-plus-gaussian-alpha-1-5</loc><lastmod>2026-05-20T09:44:24.501Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/creative-generation-on-creacof</loc><lastmod>2026-05-20T08:54:06.938Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-utility-evaluation-on-lima-original-and-rewritten-variants</loc><lastmod>2026-05-20T07:43:42.845Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generative-modeling-on-ieee-14-bus-ac-68-dim-test</loc><lastmod>2026-05-20T07:13:34.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reading-comprehension-on-squad-v2-accuracy</loc><lastmod>2026-06-02T13:53:48.899Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-flow-forecasting-on-largest-gba-original-test</loc><lastmod>2026-05-20T06:53:28.242Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-flow-forecasting-on-largest-sd-original-test</loc><lastmod>2026-05-20T06:53:28.207Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-retrieval-on-spider-lite-2-0-test</loc><lastmod>2026-05-20T06:43:25.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-retrieval-on-bird-union-test</loc><lastmod>2026-05-20T06:43:25.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-retrieval-on-spider-union-test</loc><lastmod>2026-05-20T06:43:25.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-flux-1-1024x1024-resolution-dev</loc><lastmod>2026-05-19T13:53:17.966Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-smd-f1-score</loc><lastmod>2026-05-19T13:23:09.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-evaluation-on-crc-100k</loc><lastmod>2026-05-19T13:13:05.653Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-robustness-evaluation-on-crc-100k</loc><lastmod>2026-05-19T13:13:05.611Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physical-plausibility-evaluation-on-videophy-hard-2</loc><lastmod>2026-05-28T09:11:53.232Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-2wikimulti</loc><lastmod>2026-05-19T12:36:00.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-stqa-l</loc><lastmod>2026-05-19T12:32:53.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-stqa-n</loc><lastmod>2026-05-19T12:32:53.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/infrared-small-target-detection-on-daub</loc><lastmod>2026-05-19T12:32:53.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rhetorical-role-labeling-on-deeprhole-test</loc><lastmod>2026-05-19T12:03:05.132Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rhetorical-role-labeling-on-scotussteps-test</loc><lastmod>2026-05-19T12:03:05.065Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rhetorical-role-labeling-on-scotusrf-test</loc><lastmod>2026-05-19T12:03:05.036Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-rsme-bench</loc><lastmod>2026-05-19T11:52:57.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-choice</loc><lastmod>2026-05-19T11:52:57.263Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-segmentation-on-abd-ct-setting-1</loc><lastmod>2026-06-16T09:50:56.025Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-climbmix-fineweb-edu-1m-token-val</loc><lastmod>2026-05-19T11:42:37.701Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-ocr</loc><lastmod>2026-06-30T10:24:54.934Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-learning-efficiency-on-mixed-tabular-datasets-adult-default-shoppers-magic-beijing-news</loc><lastmod>2026-05-19T11:12:28.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-segmentation-on-hrsod</loc><lastmod>2026-05-19T11:03:29.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-segmentation-on-thinobject5k-test</loc><lastmod>2026-05-19T11:03:29.736Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-segmentation-on-coift</loc><lastmod>2026-05-19T11:03:29.688Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-segmentation-on-dis5k-vd</loc><lastmod>2026-05-19T11:03:29.657Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-amc23-amc24-aime24-aime25-math500</loc><lastmod>2026-05-19T10:55:55.354Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiclass-classification-on-lycos-2017</loc><lastmod>2026-05-19T10:52:23.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/malicious-tool-call-detection-on-trust-bench-reconstructed-comparison-set-curated-1-970-episode-test</loc><lastmod>2026-05-19T10:42:20.361Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-segmentation-on-mri-47-anatomical-and-pathological-targets-samri-performance-evaluation-test</loc><lastmod>2026-05-19T10:36:05.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-understanding-on-longbench-17-metric-performance-profile</loc><lastmod>2026-05-19T10:22:12.498Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/function-calling-on-bfcl-memory</loc><lastmod>2026-05-19T09:33:53.595Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stochastic-route-planning-on-sop-stochastic-orienteering-problem-n-500-nodes</loc><lastmod>2026-05-19T09:21:53.112Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-classification-on-20-task-clip-evaluation-suite-test</loc><lastmod>2026-05-19T09:01:45.655Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/misclassification-explanation-evaluation-on-imagenet-1k-misclassified-samples-1-0-test</loc><lastmod>2026-05-19T08:51:45.024Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/textual-explanation-faithfulness-evaluation-on-imagenet-1k-1-000-images-sampled-test</loc><lastmod>2026-05-19T08:51:44.954Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/goal-conditioned-visual-planning-on-coin-t-4-71</loc><lastmod>2026-05-19T08:31:36.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/goal-conditioned-visual-planning-on-coin-t-3-71</loc><lastmod>2026-05-19T08:31:36.813Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reinforcement-learning-on-hill-car-mdp</loc><lastmod>2026-05-19T08:09:55.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mountain-car-on-mountain-car-mean-return-evaluation</loc><lastmod>2026-05-19T08:09:55.520Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/controllable-image-generation-and-editing-on-celeba-hq-test</loc><lastmod>2026-05-19T07:51:25.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/facial-image-editing-on-affectnet</loc><lastmod>2026-05-19T07:51:25.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-image-controllability-and-editing-on-affecthuman-43k-test</loc><lastmod>2026-05-19T07:51:25.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-editing-on-pie-bench-large-edits-random-images-140-images</loc><lastmod>2026-05-19T07:18:20.349Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-design-prediction-on-pew-plus-charxiv-test</loc><lastmod>2026-05-19T07:05:11.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-design-prediction-on-pewresearch-test</loc><lastmod>2026-05-19T07:05:11.717Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/honesty-alignment-on-hhh-alignment</loc><lastmod>2026-05-19T07:03:10.501Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-steering-on-steering-evaluation-concepts-llama-3-3-70b-test</loc><lastmod>2026-05-19T06:18:36.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-steering-on-gemma-2-2b-steering-evaluation-set</loc><lastmod>2026-05-19T06:18:36.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/activation-steering-on-20-steering-concepts</loc><lastmod>2026-05-19T06:18:36.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-model-evaluation-on-rewardbench-spearman</loc><lastmod>2026-05-18T08:59:06.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-ranking-on-yelp</loc><lastmod>2026-05-18T08:59:06.199Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-understanding-on-longbench-2024-test</loc><lastmod>2026-05-18T08:41:55.944Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-element-localization-on-screenspot-pro</loc><lastmod>2026-05-18T08:32:18.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-reconstruction-on-bonn-test</loc><lastmod>2026-05-18T08:28:11.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-manipulation-on-rlbench-10</loc><lastmod>2026-05-18T07:37:55.312Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-v5-test</loc><lastmod>2026-06-05T08:44:29.276Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-commonsense-reasoning-arc-e-arc-c-hellaswag-winogrande-boolq-obqa-rte-copa-race</loc><lastmod>2026-05-18T07:27:51.659Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zonal-geostrophic-current-forecasting-on-glo12-analysis-track</loc><lastmod>2026-05-18T07:21:57.581Z</lastmod></url></urlset>