<?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/text-grounding-on-vwb-eg</loc><lastmod>2026-04-28T09:21:36.938Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-grounding-on-motif</loc><lastmod>2026-04-28T09:21:36.906Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/functionality-grounding-on-funcpred</loc><lastmod>2026-04-28T09:21:36.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/attention-only-performance-evaluation-on-clip</loc><lastmod>2026-04-28T09:13:32.822Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ood-detection-on-imagenet100-id-vs-sun-ood-test</loc><lastmod>2026-05-21T11:34:41.021Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/disease-diagnosis-on-mimic-iv-ext-cardiac-disease-test</loc><lastmod>2026-04-28T08:50:50.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-diagnosis-identification-on-mimic-iv-ext-cardiac-disease</loc><lastmod>2026-04-28T08:50:50.878Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-hle-ood</loc><lastmod>2026-04-28T08:40:46.280Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-hle-test</loc><lastmod>2026-04-28T08:40:46.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-decision-making-on-scienceworld-ood</loc><lastmod>2026-04-28T08:40:46.199Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-decision-making-on-scienceworld-test</loc><lastmod>2026-04-28T08:40:46.152Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-yelp-h-n-at-5-10</loc><lastmod>2026-04-28T08:10:34.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-augmentation-on-custom-knowledge-benchmark-250-question</loc><lastmod>2026-04-28T08:00:32.859Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-segmentation-on-busi-30-percent-labels</loc><lastmod>2026-04-28T07:50:27.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-segmentation-on-busi-10-percent-labels</loc><lastmod>2026-04-28T07:50:27.585Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-segmentation-on-bcss-30-percent-labels</loc><lastmod>2026-04-28T07:50:27.549Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-image-segmentation-on-bcss-10-percent-labels</loc><lastmod>2026-04-28T07:50:27.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/contact-rich-manipulation-on-consolidated-real-world-manipulation-dataset-eval</loc><lastmod>2026-04-28T07:50:27.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binding-affinity-prediction-on-lba</loc><lastmod>2026-04-28T07:40:23.089Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-img12-val</loc><lastmod>2026-04-28T07:40:22.817Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/average-treatment-effect-estimation-on-simulation-linear-scenario-sample-size-100-test</loc><lastmod>2026-04-28T07:32:22.998Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/statement-autoformalisation-on-formalphysics-corpus</loc><lastmod>2026-04-28T07:20:18.309Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/process-reward-modeling-on-processbench-1-0-test</loc><lastmod>2026-04-28T07:20:16.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-t_od</loc><lastmod>2026-04-28T07:15:15.167Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pose-based-event-segmentation-on-f3set-tennis-100-clip-few-shot-sub</loc><lastmod>2026-04-28T07:02:35.760Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pose-based-event-segmentation-on-f3set-tennis-50-clip-few-shot-sub</loc><lastmod>2026-04-28T07:02:35.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-evaluation-on-long-context-benchmark</loc><lastmod>2026-04-28T07:00:08.062Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-llm-adapters-understanding</loc><lastmod>2026-04-28T07:00:08.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-llm-adapters-reasoning-boolq-piqa-siqa-hellaswag-arc-c</loc><lastmod>2026-04-28T07:00:07.981Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-arc-c-t-u-f-rely-metrics</loc><lastmod>2026-04-28T07:00:07.929Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-bioasq-t-u-f-rely</loc><lastmod>2026-04-28T07:00:07.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-t-u-f-rely</loc><lastmod>2026-04-28T07:00:07.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-t-u-f-rely-metrics</loc><lastmod>2026-04-28T07:00:07.817Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-alignx-ugc</loc><lastmod>2026-04-28T06:50:58.802Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-alignx-pair</loc><lastmod>2026-04-28T06:50:58.770Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-alignx-demo</loc><lastmod>2026-04-28T06:50:58.742Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-alignx-arbitrary</loc><lastmod>2026-04-28T06:50:58.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-slideasr-1-0-r</loc><lastmod>2026-04-28T06:50:04.385Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-slideasr-s-zh-1-0</loc><lastmod>2026-04-28T06:50:04.349Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-slideasr-s-en-1-0</loc><lastmod>2026-04-28T06:50:04.311Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-commonsense-reasoning-benchmark-intra-domain-multi-task</loc><lastmod>2026-04-28T06:50:04.190Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-natural-language-processing-on-cross-domain-multi-task-nlp-datasets</loc><lastmod>2026-04-28T06:50:04.148Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-signal-control-on-manhattan-28x7</loc><lastmod>2026-04-28T06:40:00.317Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-signal-control-on-manhattan-16-3</loc><lastmod>2026-04-28T06:40:00.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traffic-signal-control-on-hangzhou-4x4</loc><lastmod>2026-04-28T06:40:00.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-gtsrb-accm-and-p-value</loc><lastmod>2026-04-27T07:29:49.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-speaker-automatic-speech-recognition-on-ami-sdm-test</loc><lastmod>2026-06-11T10:32:54.895Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-object-localization-on-lerf</loc><lastmod>2026-05-14T09:41:50.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermark-detection-on-humaneval-tpr-f1-at-1-percent-and-5-percent-fpr</loc><lastmod>2026-04-27T07:20:30.515Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-pass-at-1-tpr-f1-vs-fpr</loc><lastmod>2026-04-27T07:20:30.430Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-reinforcement-learning-on-ogbench-cube-single-singletask-5-tasks</loc><lastmod>2026-05-29T09:41:56.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-safety-and-pedagogical-evaluation-on-shape</loc><lastmod>2026-04-27T06:50:41.939Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phoneme-recognition-on-l2-arctic-test</loc><lastmod>2026-04-27T06:50:11.698Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mispronunciation-diagnosis-on-l2-arctic-test</loc><lastmod>2026-04-27T06:50:11.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-pole-striking-on-ropes-in-domain-brown-yellow-red-orange</loc><lastmod>2026-04-27T06:49:34.458Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-understanding-on-glue-cola-mrpc-qnli-rte-sts-b-sst-2</loc><lastmod>2026-04-24T08:52:06.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-portfolio-allocation-on-d-full-frozen-test</loc><lastmod>2026-04-24T08:42:00.178Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/longitudinal-affect-assessment-on-semeval-2026-task-2-subtask-1-dev</loc><lastmod>2026-04-24T08:23:49.333Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-reasoning-on-mme-rw-chinese</loc><lastmod>2026-04-24T08:11:40.915Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-navigation-on-textnav</loc><lastmod>2026-05-08T10:27:38.686Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geocoding-on-base-data-rural</loc><lastmod>2026-04-24T08:06:36.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generalized-referring-expression-segmentation-on-earthreason-test</loc><lastmod>2026-04-24T07:50:51.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/neurodevelopmental-disorder-diagnosis-on-adhd-200-schaefer-atlas-test</loc><lastmod>2026-04-24T07:37:42.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnosis-on-adhd-200-aal116-atlas-test</loc><lastmod>2026-04-24T07:37:41.843Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnostic-classification-on-abide-i-schaefer-atlas</loc><lastmod>2026-04-24T07:37:41.792Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-grounding-on-ui-vision-spatial</loc><lastmod>2026-04-24T07:31:08.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-grounding-on-ui-vision-functional</loc><lastmod>2026-04-24T07:31:08.404Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-grounding-on-ui-vision-basic</loc><lastmod>2026-04-24T07:31:08.377Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-win-rate-estimation-ranking-on-llm-benchmark-appendix</loc><lastmod>2026-04-24T07:30:37.950Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cloud-top-height-cth-regression-on-hyperfm-250k</loc><lastmod>2026-04-24T07:18:44.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cloud-water-path-cwp-regression-on-hyperfm250k</loc><lastmod>2026-04-24T07:18:44.781Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cloud-effective-radius-cer-regression-on-hyperfm250k</loc><lastmod>2026-04-24T07:18:44.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cloud-optical-thickness-cot-regression-on-hyperfm250k</loc><lastmod>2026-04-24T07:18:44.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-ogbn-arxiv-accuracy-and-acc</loc><lastmod>2026-05-13T07:01:56.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/alignment-faking-diagnosis-on-vlaf</loc><lastmod>2026-04-24T07:08:41.198Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/alignment-faking-diagnosis-on-prior-diagnostics</loc><lastmod>2026-04-24T07:08:41.157Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-mlvp-test</loc><lastmod>2026-04-24T07:00:48.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-msrvtt-1ka-severity-degree-4</loc><lastmod>2026-04-24T07:00:48.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-msrvtt-severity-degree-1-1ka</loc><lastmod>2026-04-24T07:00:48.227Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-activitynet-severity-degree-5-test</loc><lastmod>2026-04-24T07:00:48.158Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-lsmdc-robustness-metrics</loc><lastmod>2026-04-24T07:00:48.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-retrieval-on-activitynet-lsmdc-activitynet</loc><lastmod>2026-04-24T07:00:48.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-retrieval-on-activitynet-lsmdc</loc><lastmod>2026-04-24T07:00:48.066Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-retrieval-on-msrvtt-1ka-query-shift-test</loc><lastmod>2026-04-24T07:00:47.933Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-msrvtt-1ka-severity-degree-3</loc><lastmod>2026-04-24T07:00:47.902Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-retrieval-on-msvd-1ka-test</loc><lastmod>2026-04-24T07:00:47.867Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-msrvtt-1ka-noise-robustness</loc><lastmod>2026-04-24T07:00:47.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-video-retrieval-on-lsmdc-test-using-linguistic-metrics</loc><lastmod>2026-04-24T07:00:47.720Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-text-retrieval-on-didemo-corruption-robustness</loc><lastmod>2026-04-24T07:00:47.609Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-amazon-electronics-hr-at-10-ndcg-at-10-mrr</loc><lastmod>2026-04-24T06:58:35.769Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mechanism-of-action-classification-on-jump-cp-s8-s6</loc><lastmod>2026-04-23T11:28:28.846Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mechanism-of-action-moa-classification-on-jump-cp-s3-s6</loc><lastmod>2026-04-23T11:28:28.809Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mechanism-of-action-classification-on-jump-cp-s8-s3</loc><lastmod>2026-04-23T11:28:28.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mechanism-of-action-classification-on-jump-cp-s3-s8</loc><lastmod>2026-04-23T11:28:28.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-reference-image-editing-on-mico-bench</loc><lastmod>2026-05-13T10:32:47.164Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-preference-evaluation-on-ultrafeedback-test</loc><lastmod>2026-07-07T07:09:01.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-incremental-learning-on-seq-cifar-100</loc><lastmod>2026-04-23T11:08:20.594Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quadruple-consistency-evaluation-on-cctvbench</loc><lastmod>2026-04-23T10:48:51.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/linguistic-steganography-on-cover-stego-dataset-test</loc><lastmod>2026-04-23T10:33:06.716Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-amazon-reviews-arts-crafts-and-sewing</loc><lastmod>2026-04-23T10:02:15.921Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-amazon-reviews-sports-and-outdoors</loc><lastmod>2026-04-23T10:02:15.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-amazon-reviews-toys-and-games</loc><lastmod>2026-04-23T10:02:15.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/recommendation-on-amazon-reviews-beauty-and-personal-care</loc><lastmod>2026-04-23T10:02:15.822Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inertial-odometry-on-ronin-unseen</loc><lastmod>2026-07-07T08:44:49.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inertial-odometry-on-ronin-seen</loc><lastmod>2026-07-07T08:44:49.446Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-condaqa-val</loc><lastmod>2026-04-23T09:27:54.965Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-reasoning-on-nevir</loc><lastmod>2026-04-23T09:27:54.905Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-mnli-neg</loc><lastmod>2026-04-23T09:27:54.872Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-snli-neg</loc><lastmod>2026-04-23T09:27:54.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-rte-neg-accuracy</loc><lastmod>2026-04-23T09:27:54.807Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-telugu-medical-domain-database</loc><lastmod>2026-04-23T09:21:51.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-cause-pair-extraction-in-conversations-on-ecf</loc><lastmod>2026-04-23T08:57:32.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-atrdf-2023</loc><lastmod>2026-04-23T08:48:01.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-soyglobal</loc><lastmod>2026-04-23T08:40:53.781Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-soygene</loc><lastmod>2026-04-23T08:40:53.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-soyloc</loc><lastmod>2026-04-23T08:40:53.729Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cotton80</loc><lastmod>2026-04-23T08:40:53.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-visual-classification-on-soyglobal</loc><lastmod>2026-04-23T08:37:25.816Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-visual-classification-on-soyageing</loc><lastmod>2026-04-23T08:37:25.785Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-visual-classification-on-soygene</loc><lastmod>2026-04-23T08:37:25.748Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-visual-classification-on-soyloc</loc><lastmod>2026-04-23T08:37:25.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-visual-classification-on-cotton80</loc><lastmod>2026-04-23T08:37:25.676Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-grounding-on-screenspot-v2-device-input-modality-breakdown</loc><lastmod>2026-04-23T08:28:14.704Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-essay-scoring-on-ellipse</loc><lastmod>2026-04-23T08:06:24.977Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-generation-on-beijing-original-test</loc><lastmod>2026-04-23T07:47:41.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-generation-on-magic-original-test</loc><lastmod>2026-04-23T07:47:40.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-synthesis-on-average-of-4-datasets-excluding-beijing</loc><lastmod>2026-04-23T07:47:40.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-synthesis-on-average-of-5-datasets-adult-shoppers-beijing-and-two-others</loc><lastmod>2026-04-23T07:47:40.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-alignment-on-beijing-dataset</loc><lastmod>2026-04-23T07:47:40.564Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-generation-on-magic-alpha-precision-beta-recall-c2st</loc><lastmod>2026-04-23T07:47:40.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-generation-on-shoppers-alpha-precision-beta-recall-c2st</loc><lastmod>2026-04-23T07:47:40.443Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-generation-on-adult-alpha-precision-beta-recall-c2st</loc><lastmod>2026-04-23T07:47:40.379Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ai-reasoning-on-arc-easy-held-out</loc><lastmod>2026-04-23T07:28:01.451Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-glass-ari-fm-vm</loc><lastmod>2026-06-18T08:12:59.288Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-pku-saferlhf</loc><lastmod>2026-06-23T11:52:01.747Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-and-reasoning-on-sudoku</loc><lastmod>2026-04-23T07:10:53.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-and-reasoning-on-countdown-accuracy</loc><lastmod>2026-04-23T07:10:53.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-robot-task-and-motion-planning-on-ev-battery-disassembly</loc><lastmod>2026-04-23T06:56:51.119Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-tuning-for-knowledge-acquisition-and-abstention-preservation-on-rwd</loc><lastmod>2026-04-23T06:46:48.361Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-tuning-for-knowledge-acquisition-and-abstention-preservation-on-tofu</loc><lastmod>2026-04-23T06:46:48.320Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-tuning-for-knowledge-acquisition-and-abstention-preservation-on-pistol</loc><lastmod>2026-04-23T06:46:48.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-augmented-reasoning-on-pymath-test</loc><lastmod>2026-04-23T06:16:45.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/forecasting-on-fb-a-b</loc><lastmod>2026-04-21T13:53:42.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-reasoning-on-drivebench</loc><lastmod>2026-04-21T13:36:38.194Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-and-3d-understanding-on-stride-qa</loc><lastmod>2026-04-21T13:36:38.119Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-multi-domain-language-evaluation-suite-various</loc><lastmod>2026-04-21T13:33:26.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rtl-design-optimization-on-60-circuits</loc><lastmod>2026-04-21T13:29:54.730Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-factual-generation-on-longfact</loc><lastmod>2026-04-21T13:26:34.612Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-rag-evaluation-on-ragchecker</loc><lastmod>2026-04-21T13:26:34.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-retrieval-augmented-generation-on-longfact</loc><lastmod>2026-04-21T13:26:34.532Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-f1-collapse-point</loc><lastmod>2026-04-21T13:06:43.211Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-f1-collapse-point</loc><lastmod>2026-04-21T13:06:43.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-f1-collapse-point</loc><lastmod>2026-04-21T13:06:43.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-f1-score-collapse-point</loc><lastmod>2026-04-21T13:06:43.093Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/braking-intensity-prediction-on-human-in-the-loop-simulation-h-s</loc><lastmod>2026-04-21T13:06:30.156Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-kina-rutul-evaluation</loc><lastmod>2026-04-21T13:06:29.368Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-archi-evaluation</loc><lastmod>2026-04-21T13:06:29.292Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-robot-path-planning-on-empty-2-robots-max-vel-0-703</loc><lastmod>2026-04-21T12:56:27.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val-zero-shot-accuracy</loc><lastmod>2026-04-21T12:56:27.164Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerability-injection-on-cweval-python</loc><lastmod>2026-04-21T12:50:31.757Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bug-injection-on-mbpp-plus</loc><lastmod>2026-04-21T12:50:31.725Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bug-injection-on-humaneval-plus</loc><lastmod>2026-04-21T12:50:31.701Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/authorship-discernment-on-authorship-discernment-dataset</loc><lastmod>2026-04-21T12:29:43.066Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-reconstruction-on-codec-superb-tiny-speech</loc><lastmod>2026-04-21T12:06:13.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-lambada</loc><lastmod>2026-04-21T11:56:10.187Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/modulation-classification-on-radioml-50-s-cls-2016-10a</loc><lastmod>2026-04-21T11:56:09.730Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/modulation-classification-on-radioml-25-s-cls-2016-10a</loc><lastmod>2026-04-21T11:56:09.691Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/modulation-classification-on-radioml-10-s-cls-2016-10a</loc><lastmod>2026-04-21T11:56:09.648Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interference-classification-on-ic-dataset-50-s-cls</loc><lastmod>2026-04-21T11:56:09.607Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interference-classification-on-ic-dataset-25-s-cls</loc><lastmod>2026-04-21T11:56:09.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interference-classification-on-ic-dataset-10-s-cls</loc><lastmod>2026-04-21T11:50:17.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/point-cloud-registration-on-color3dlomatch-c3dlm-indoor</loc><lastmod>2026-04-21T11:46:07.423Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/point-cloud-registration-on-color3dmatch-c3dm-indoor</loc><lastmod>2026-04-21T11:46:07.391Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-mcql</loc><lastmod>2026-04-21T11:28:31.675Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-question-answering-on-environmental-report</loc><lastmod>2026-04-21T11:25:59.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-question-answering-on-world-history</loc><lastmod>2026-04-21T11:25:59.226Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/latency-and-gpu-energy-consumption-on-pdebench-for-burgers-equation</loc><lastmod>2026-04-21T11:05:53.179Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/1d-diffusion-sorption-on-pdebench-latency-and-energy</loc><lastmod>2026-04-21T11:05:53.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/1d-diffusion-reaction-on-pdebench-latency-gpu-energy-consumption</loc><lastmod>2026-04-21T11:05:53.106Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-plausibility-estimation-free-form-text-on-cfc</loc><lastmod>2026-04-21T10:45:47.783Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-guided-selective-generation-on-triviaqa-val</loc><lastmod>2026-04-21T10:45:47.244Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-triviaqa-val</loc><lastmod>2026-04-21T10:45:47.206Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-guided-selective-generation-on-coqa-dev</loc><lastmod>2026-04-21T10:45:47.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-coqa-dev</loc><lastmod>2026-04-21T10:45:47.130Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-goal-conditioned-reinforcement-learning-on-humanoidmaze-large-navigate-v0</loc><lastmod>2026-05-21T11:08:22.379Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-goal-conditioned-reinforcement-learning-on-antmaze-medium-navigate-v0</loc><lastmod>2026-04-21T10:35:44.527Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/political-and-legal-affairs-assessment-on-polilegal</loc><lastmod>2026-04-21T10:35:44.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counterfactual-explanation-on-moons-5-fold-synthetic-test</loc><lastmod>2026-04-21T10:35:43.090Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-em-f1-p-r</loc><lastmod>2026-04-21T10:25:39.793Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1-p-r</loc><lastmod>2026-04-21T10:25:39.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grounded-multimodal-entity-recognition-on-twitter-fmnerg-test</loc><lastmod>2026-04-21T10:15:35.596Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-assessment-on-safety-avg</loc><lastmod>2026-04-21T10:07:57.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prosocial-safety-assessment-on-prosocial</loc><lastmod>2026-04-21T10:07:56.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/helpful-and-harmless-response-generation-on-pku-saferlhf-alpaca2-7b-test</loc><lastmod>2026-04-21T10:07:26.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-average-gsm8k-math-500-amc23</loc><lastmod>2026-04-21T10:06:56.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-average-tokens-token-efficiency</loc><lastmod>2026-04-21T10:06:56.421Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-average-tokens-token-efficiency</loc><lastmod>2026-04-21T10:06:56.392Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/professional-multimodal-understanding-on-mmmu-pro</loc><lastmod>2026-04-21T10:05:33.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-question-answering-on-scienceqa-calibration-ranking-metrics</loc><lastmod>2026-04-21T10:05:33.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-consistency-evaluation-on-conbench</loc><lastmod>2026-04-21T10:05:32.987Z</lastmod></url></urlset>