<?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/mathematical-reasoning-on-math-500-accuracy-token-usage-compression-ratio</loc><lastmod>2026-05-19T10:32:16.556Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-token-usage-compression-ratio</loc><lastmod>2026-05-19T10:32:16.519Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-on-advbench-80-20-test</loc><lastmod>2026-05-19T10:32:16.057Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-cifar-100-50-percent-random-data-removal</loc><lastmod>2026-05-19T10:22:55.917Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-cifar-100-10-percent-random-data-removal</loc><lastmod>2026-05-19T10:22:55.844Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/item-to-item-retrieval-on-e-commerce-dataset-test</loc><lastmod>2026-05-19T10:12:09.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/research-task-on-liveresearchbench-lrb</loc><lastmod>2026-05-19T09:34:53.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/research-task-on-deepresearchbench-drb</loc><lastmod>2026-05-19T09:34:53.953Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-task-on-pinchbench-pb</loc><lastmod>2026-05-19T09:34:53.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-domain-capability-retention-on-aime-2024-math-500-gsm8k-humaneval-mmlu</loc><lastmod>2026-05-19T08:51:44.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arithmetic-function-acquisition-on-kgfunc-unseen-accuracy</loc><lastmod>2026-05-19T08:51:44.371Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arithmetic-function-acquisition-on-kgfunc-test</loc><lastmod>2026-05-19T08:51:44.327Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-book-question-answering-on-simpleqa-train</loc><lastmod>2026-05-19T08:51:44.209Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-capability-retention-on-held-out-capability-average</loc><lastmod>2026-05-19T08:51:44.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-accuracy-percent</loc><lastmod>2026-05-19T08:51:44.142Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-recall-on-kgfact-retrieval</loc><lastmod>2026-05-19T08:51:44.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-book-recall-on-kgfact-small-train</loc><lastmod>2026-05-19T08:51:44.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unsupervised-outlier-model-selection-on-39-tabular-benchmark-datasets</loc><lastmod>2026-05-19T07:45:42.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/real-world-multimodal-understanding-on-realworldqa-accuracy</loc><lastmod>2026-05-27T08:23:47.185Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arrhythmia-classification-on-vitaldb</loc><lastmod>2026-05-19T07:23:25.813Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arrhythmia-classification-on-incart</loc><lastmod>2026-05-19T07:23:25.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arrhythmia-classification-on-mit-bih-sup</loc><lastmod>2026-05-19T07:23:25.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arrhythmia-classification-on-mit-bih</loc><lastmod>2026-05-19T07:23:25.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counterfactual-explanations-on-compas</loc><lastmod>2026-06-01T08:30:20.751Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reentrant-network-modeling-on-reentrant-network</loc><lastmod>2026-05-19T06:18:37.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-dtd-synthetic-1-test</loc><lastmod>2026-05-18T09:19:18.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ifeval-strict-accuracy</loc><lastmod>2026-05-18T08:38:15.668Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/competitive-programming-on-livecodebench-accuracy</loc><lastmod>2026-05-18T08:38:15.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-level-5-pass-at-1</loc><lastmod>2026-05-20T07:09:03.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-mllmu-bench-5-percent-forget-real</loc><lastmod>2026-05-18T07:58:02.304Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-mllmu-bench-5-percent-forget-test</loc><lastmod>2026-05-18T07:58:02.266Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-commonsense-reasoning-on-piqa-hellaswag-winogrande-arc-easy-openbookqa-and-mathqa-test</loc><lastmod>2026-05-18T07:58:00.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-codecontests-pass-at-1</loc><lastmod>2026-05-25T07:32:34.085Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/on-time-arrival-probability-estimation-on-sioux-falls-network-sfn</loc><lastmod>2026-05-18T06:37:33.347Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-mesh-recovery-on-emdb-1</loc><lastmod>2026-06-29T06:53:28.147Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-dimensional-bayesian-optimization-on-humanoid-d-6392</loc><lastmod>2026-05-21T10:00:01.430Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-muse-news-extraction-strength-knowmem-rouge</loc><lastmod>2026-06-04T07:18:35.808Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-tofu-llama-3-2-1b-split99</loc><lastmod>2026-05-15T07:27:55.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ifeval-improvement-score</loc><lastmod>2026-06-15T06:31:25.104Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-generation-on-vbench-augmented-prompts</loc><lastmod>2026-05-14T09:56:02.679Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spectral-super-resolution-on-ih-10</loc><lastmod>2026-05-14T09:46:01.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-reconstruction-on-ffhq-1k</loc><lastmod>2026-05-14T09:38:48.484Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-detection-on-comment-dataset-out-of-distribution</loc><lastmod>2026-05-14T07:35:15.779Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-detection-on-posts-dataset-out-of-distribution</loc><lastmod>2026-05-14T07:35:15.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-detection-on-comment-dataset-in-distribution</loc><lastmod>2026-05-14T07:35:15.722Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-detection-on-posts-dataset-in-distribution</loc><lastmod>2026-05-14T07:35:15.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/motion-planning-on-assemblybench</loc><lastmod>2026-05-14T07:35:15.474Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phenotype-extraction-on-csc-n-116-docs</loc><lastmod>2026-05-14T06:44:58.400Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-mitigation-on-hallusionbench-visual-dependent-setting-test</loc><lastmod>2026-05-14T06:44:57.291Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-presence-detection-on-pope-average-ms-coco-a-okvqa-gqa</loc><lastmod>2026-05-14T06:44:57.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-grounding-on-cuactspot</loc><lastmod>2026-05-13T11:36:29.272Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/complex-infographic-generation-on-bizgeneval-easy-test</loc><lastmod>2026-05-13T11:35:56.216Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/complex-infographic-generation-on-bizgeneval-hard-test</loc><lastmod>2026-05-13T11:35:56.166Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-alignment-on-logiqa</loc><lastmod>2026-05-13T11:24:49.235Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-calibration-on-reclor-test</loc><lastmod>2026-05-13T11:24:49.197Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-accuracy-ece-aurc-spearman</loc><lastmod>2026-05-13T11:24:49.152Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-evaluation-on-pope-overall</loc><lastmod>2026-05-15T07:09:44.199Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-range-interaction-modeling-on-lrim-16-hard</loc><lastmod>2026-05-19T13:07:56.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-and-reasoning-on-mme-realworld-lite</loc><lastmod>2026-06-24T08:07:26.369Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-qa-retrieval-on-musique-r-at-2-r-at-5-avg-rank</loc><lastmod>2026-05-13T10:24:28.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/camera-pose-estimation-on-dycheck-ate-rte-rre</loc><lastmod>2026-06-30T07:18:04.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-geo3k-accuracy</loc><lastmod>2026-06-23T12:22:23.576Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-robustbench-tc-perturbed-1-0-test</loc><lastmod>2026-05-13T10:04:22.115Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-robustbench-tc-clean-1-0-test</loc><lastmod>2026-05-13T10:04:22.069Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/depth-estimation-on-nyu-v2-regional-metrics</loc><lastmod>2026-06-01T10:33:13.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-fashion-overall</loc><lastmod>2026-05-13T09:14:08.492Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-steam-head-item</loc><lastmod>2026-05-13T09:14:08.461Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-steam-tail-item</loc><lastmod>2026-05-13T09:14:08.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/depth-estimation-on-eth3d-absrel-delta1</loc><lastmod>2026-05-15T10:05:11.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-agent-task-execution-under-injection-on-clawbench-overall</loc><lastmod>2026-05-13T08:23:53.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-agent-task-execution-under-injection-on-clawbench-dev</loc><lastmod>2026-05-13T08:23:53.491Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-agent-task-execution-under-injection-on-clawbench-office</loc><lastmod>2026-05-13T08:23:53.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-agent-task-execution-under-injection-on-clawbench-daily-life</loc><lastmod>2026-05-13T08:23:53.420Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-agent-task-execution-under-injection-on-clawbench-social</loc><lastmod>2026-05-13T08:23:53.387Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/major-depressive-disorder-detection-on-mdd</loc><lastmod>2026-05-13T08:14:52.800Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-recognition-on-ssv2-train-test</loc><lastmod>2026-05-13T08:03:44.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-recognition-on-hmdb51-train-test</loc><lastmod>2026-05-13T08:03:44.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerable-agent-identification-on-battle-environment-144-agents-72-adversaries</loc><lastmod>2026-05-13T07:54:11.081Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerable-agent-identification-on-battle-environment-64-agents-32-adversaries</loc><lastmod>2026-05-13T07:54:11.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-temporal-grounding-on-charades</loc><lastmod>2026-05-13T06:43:23.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/exploitability-minimization-on-double-board-hunl</loc><lastmod>2026-05-12T17:00:36.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-synthesis-on-imagenet-256x256</loc><lastmod>2026-06-05T09:12:46.274Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/segmentation-on-ham10000-hard-samples</loc><lastmod>2026-05-12T16:08:35.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ifeval-ifscore</loc><lastmod>2026-05-15T09:59:37.507Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-biokg-test</loc><lastmod>2026-05-12T15:55:55.658Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-radiotherapy-target-segmentation-on-multimodal-3d-radiotherapy-target-dataset-all-samples</loc><lastmod>2026-05-12T15:52:59.072Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-pok-mon</loc><lastmod>2026-05-29T09:50:00.143Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pairwise-preference-evaluation-on-common2sense</loc><lastmod>2026-05-12T15:23:39.384Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-forecasting-on-weather-horizon-96</loc><lastmod>2026-05-15T07:11:15.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-deepfake-detection-on-wavefake-average-test</loc><lastmod>2026-05-12T14:47:47.132Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-deepfake-detection-on-wavefake-waveglow-test</loc><lastmod>2026-05-12T14:47:47.095Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-deepfake-detection-on-wavefake-pwg-test</loc><lastmod>2026-05-12T14:47:47.067Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-deepfake-detection-on-wavefake-hifi-gan-test</loc><lastmod>2026-05-12T14:47:47.018Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-deepfake-detection-on-wavefake-melgan-l-test</loc><lastmod>2026-05-12T14:47:46.967Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/forward-pde-solving-on-forward-benchmarks-5-pdes</loc><lastmod>2026-05-12T14:45:14.684Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-domain-llm-evaluation-on-mmlu-gsm8k-multiarith-svamp-aqua-and-humaneval</loc><lastmod>2026-05-12T13:55:44.238Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/macd-prediction-on-finance-30-days</loc><lastmod>2026-05-12T14:21:01.634Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/macd-prediction-on-finance-7-days</loc><lastmod>2026-05-12T14:21:01.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-discovery-on-lr-gaussian-20-20-2</loc><lastmod>2026-05-12T13:22:10.838Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-discovery-on-lr-gaussian-10-10-2</loc><lastmod>2026-05-12T13:22:10.803Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/brain-decoding-on-seed-iv</loc><lastmod>2026-05-19T12:41:07.769Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-mmmu-pro-mean-at-8-acc-percent</loc><lastmod>2026-05-12T12:41:57.480Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-system-task-solving-on-workbench</loc><lastmod>2026-05-12T12:31:55.347Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-system-task-solving-on-plancraft</loc><lastmod>2026-05-12T12:31:55.311Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-system-task-solving-on-browsecomp</loc><lastmod>2026-05-12T12:31:55.278Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-system-task-solving-on-finance</loc><lastmod>2026-05-12T12:31:55.245Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-answer-question-answering-on-natural-questions-nq</loc><lastmod>2026-05-12T12:21:53.024Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-answer-question-answering-on-triviaqa</loc><lastmod>2026-05-12T12:21:52.946Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-question-answering-on-truthfulqa-percent-truth-percent-info-percent-t-i-percent-reject</loc><lastmod>2026-05-12T12:21:52.908Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/class-conditional-image-generation-on-imagenet-256x256-2015-test</loc><lastmod>2026-05-12T12:06:42.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/place-recognition-on-kitti360-ag-road-map</loc><lastmod>2026-05-12T12:02:38.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/place-recognition-on-kitti360-ag-satellite</loc><lastmod>2026-05-12T12:02:38.178Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/place-recognition-on-nuscenes-ag</loc><lastmod>2026-05-12T12:02:38.118Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/context-compression-on-benchpress-short-context-test</loc><lastmod>2026-05-12T11:07:29.394Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/length-of-stay-los-on-mimic-iv</loc><lastmod>2026-06-05T09:51:14.557Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medqa-usmle-accuracy</loc><lastmod>2026-06-04T11:43:38.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-on-forge-bench</loc><lastmod>2026-05-12T10:12:26.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-commonsenseqa-csqa-test</loc><lastmod>2026-05-12T10:11:07.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-arc-challenge-arc-c-test</loc><lastmod>2026-05-12T10:11:07.650Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-view-synthesis-on-test</loc><lastmod>2026-05-12T09:40:56.717Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-view-synthesis-on-unspecified-dataset-train</loc><lastmod>2026-05-12T09:40:56.676Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/population-dynamics-interpolation-on-eb-scrna-5-dim-pca-representation-leave-one-out</loc><lastmod>2026-05-12T08:53:03.363Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-question-answering-on-gpqa-d-accuracy-mean-at-4-percent-and-speedup</loc><lastmod>2026-05-12T08:40:40.375Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-pass-at-4-accuracy-and-grpo-speedup</loc><lastmod>2026-05-12T08:40:40.342Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-accuracy-at-4-grpo-speedup</loc><lastmod>2026-05-12T08:40:40.309Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-at-4-and-grpo-speedup</loc><lastmod>2026-05-12T08:40:40.274Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-at-4-and-speedup</loc><lastmod>2026-05-12T08:40:40.239Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-discovery-on-alarm-d-37</loc><lastmod>2026-06-04T09:42:21.646Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-val-metrics-top-1-percent-pp</loc><lastmod>2026-06-02T06:57:14.384Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-3-shot-flex-and-reuse</loc><lastmod>2026-05-12T07:30:18.511Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-minerva-math-4-shot</loc><lastmod>2026-05-12T07:30:18.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-human-eval-zero-shot</loc><lastmod>2026-05-12T07:30:18.432Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reliability-prediction-on-pope-adversarial</loc><lastmod>2026-05-12T07:20:15.513Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-localization-on-looting-event-localization-dataset-test</loc><lastmod>2026-05-12T06:40:04.049Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/month-level-change-detection-on-afghanistan-archaeological-sites-test</loc><lastmod>2026-05-12T06:40:03.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-agent-user-interaction-on-tac-theagentcompany</loc><lastmod>2026-05-11T10:39:54.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-math-500-pass-at-1</loc><lastmod>2026-05-11T10:06:37.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/algorithmic-recourse-on-german-10-fold-cross-validation</loc><lastmod>2026-05-11T09:55:00.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/algorithmic-recourse-on-attrition-10-fold-cross-validation</loc><lastmod>2026-05-11T09:55:00.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/algorithmic-recourse-on-attrition</loc><lastmod>2026-05-11T09:55:00.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-bgqa-crux-stgqa-tablebench-mmlu-stem-suite</loc><lastmod>2026-05-11T09:03:50.796Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-multimodal-reasoning-on-naturalbench</loc><lastmod>2026-05-11T08:49:42.932Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-multimodal-reasoning-on-logicvista</loc><lastmod>2026-05-11T08:49:42.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-multimodal-reasoning-on-mmmu-pro</loc><lastmod>2026-05-11T08:49:42.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-math-reasoning-on-mathvista-score</loc><lastmod>2026-05-11T08:49:42.831Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/infrared-small-target-detection-on-nuaa-sirst-iou-niou-f-measure-pd-fa</loc><lastmod>2026-05-11T08:40:07.248Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/infrared-small-target-detection-on-nudt-sirst-iou-niou-f-measure-pd-fa</loc><lastmod>2026-05-11T08:40:07.213Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-beir-7-average</loc><lastmod>2026-05-11T08:38:06.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-quora-specific-ndcg-metrics</loc><lastmod>2026-05-11T08:38:06.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-arguana-ndcg-variants</loc><lastmod>2026-05-11T08:38:06.093Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-fiqa-ndcg-at-10-by-retrieval-method</loc><lastmod>2026-05-11T08:38:06.063Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-scifact-ndcg-at-10-variants</loc><lastmod>2026-05-11T08:38:06.025Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-hqa</loc><lastmod>2026-05-11T08:38:05.992Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-nq-ndcg-at-10-variants</loc><lastmod>2026-05-11T08:38:05.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-ms-marco-mrr-at-10-components</loc><lastmod>2026-05-11T08:38:05.920Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-em</loc><lastmod>2026-05-11T07:08:41.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt-2025-feb</loc><lastmod>2026-05-08T11:07:31.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-hetionet</loc><lastmod>2026-06-02T06:42:03.182Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pest-classification-on-qfsd-test</loc><lastmod>2026-05-08T10:07:57.907Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pest-classification-on-agriinsect-test</loc><lastmod>2026-05-08T10:07:57.870Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-igsm</loc><lastmod>2026-05-08T09:17:40.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-classification-on-pneumoniamnist</loc><lastmod>2026-05-27T07:55:55.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/aerodynamic-field-prediction-on-superwing-test</loc><lastmod>2026-05-08T07:58:45.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/accuracy-on-aime-25</loc><lastmod>2026-05-20T08:52:55.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-manipulation-on-can-image</loc><lastmod>2026-05-07T10:04:30.467Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-plus-image-editing-on-costa-text-plus-image-tasks-1-0-test</loc><lastmod>2026-05-07T09:44:16.960Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quadratic-nonlinear-schr-dinger-equation-t-1-0-n-1024-0-5</loc><lastmod>2026-05-07T09:18:59.485Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-hex-phi-alpaca-risk-ranked-subsets</loc><lastmod>2026-05-07T08:46:21.840Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-hex-phi-dolly-risk-ranked</loc><lastmod>2026-05-07T08:46:21.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-categoricalharmfulqa-dolly-fine-tuning-test</loc><lastmod>2026-05-07T08:46:21.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-fpha-standard-predefined</loc><lastmod>2026-05-07T08:16:10.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-recognition-on-hdm05-5-fold-stratified-cross-validation</loc><lastmod>2026-05-07T08:16:10.354Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/federated-backdoor-defense-on-emnist</loc><lastmod>2026-05-07T08:06:07.063Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/federated-backdoor-defense-on-cifar100</loc><lastmod>2026-05-07T08:06:07.023Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/alzheimer-s-disease-diagnosis-on-darwin</loc><lastmod>2026-05-07T07:35:52.404Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-conversational-question-answering-on-mmcoqa</loc><lastmod>2026-05-07T07:26:07.782Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-on-blink</loc><lastmod>2026-05-07T07:26:07.739Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/accuracy-on-physical-iqa-piqa</loc><lastmod>2026-05-06T09:03:09.228Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/survival-analysis-on-metabric</loc><lastmod>2026-06-04T09:47:55.147Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-150-dataset-fold-combinations</loc><lastmod>2026-05-06T08:47:29.798Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safeguarding-llm-agents-against-prompt-injection-on-banking-and-slack-test</loc><lastmod>2026-05-06T07:35:13.744Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agitation-score-prediction-on-bridge2ai-speaker-independent-cv</loc><lastmod>2026-05-06T07:06:35.597Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-purpose-language-evaluation-on-scan</loc><lastmod>2026-05-04T07:57:04.867Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/affordance-grounding-on-reasonaff-test</loc><lastmod>2026-05-04T07:51:32.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/distributed-training-on-llama2-13b</loc><lastmod>2026-05-04T07:45:28.698Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-classification-on-holisafe-bench-ece-nll</loc><lastmod>2026-05-04T07:23:54.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-classification-on-unsafebench-ece-nll</loc><lastmod>2026-05-04T07:23:54.944Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/derivative-recovery-on-sinusoidal-p-0-25-test</loc><lastmod>2026-05-04T07:16:43.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/wafer-defect-analysis-on-wafer-defect-analysis</loc><lastmod>2026-05-01T08:18:58.614Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/wafer-map-analysis-on-wafer-map-analysis-dataset</loc><lastmod>2026-05-01T08:18:58.581Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-ur-am-sm-ms</loc><lastmod>2026-04-30T08:12:52.009Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pointbutton2-on-safety-gymnasium</loc><lastmod>2026-04-30T07:39:05.939Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pointbutton1-on-safety-gymnasium</loc><lastmod>2026-04-30T07:39:05.902Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pointpush2-on-safety-gymnasium</loc><lastmod>2026-04-30T07:39:05.870Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pointpush1-on-safety-gymnasium</loc><lastmod>2026-04-30T07:39:05.838Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pointgoal2-on-safety-gymnasium</loc><lastmod>2026-04-30T07:39:05.803Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pointgoal1-on-safety-gymnasium</loc><lastmod>2026-04-30T07:39:05.762Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/attribute-value-extraction-on-amazon-reviews-2023</loc><lastmod>2026-04-30T07:03:40.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-reasoning-on-webaggregatorqa</loc><lastmod>2026-04-30T07:02:28.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-higgs-train</loc><lastmod>2026-04-30T06:52:25.656Z</lastmod></url></urlset>