<?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/adversarial-attack-on-llm-agents-on-gsm8k</loc><lastmod>2026-05-20T07:26:14.648Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-fineweb-edu-10k-steps-val</loc><lastmod>2026-05-20T07:13:33.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-fineweb-edu-10k-steps-train</loc><lastmod>2026-05-20T07:13:33.224Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-summarization-on-synthetic-time-series-test</loc><lastmod>2026-05-20T07:13:32.947Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-ranking-on-main-experiment</loc><lastmod>2026-05-20T06:43:25.148Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-12-binary-datasets</loc><lastmod>2026-05-19T13:48:49.323Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-range-interaction-modeling-on-lrim-hard-32</loc><lastmod>2026-05-19T13:13:04.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-detection-on-pku-davis-sod-9</loc><lastmod>2026-05-19T12:28:22.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pansharpening-on-wv3-reduced-resolution</loc><lastmod>2026-05-19T12:23:49.442Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pansharpening-on-quickbird-qb-reduced-resolution</loc><lastmod>2026-05-19T12:23:49.409Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dynamic-scene-compression-on-n3d-video-test</loc><lastmod>2026-05-19T12:10:39.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knapsack-problem-on-ks500-test</loc><lastmod>2026-05-19T12:02:44.439Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/combinatorial-auction-knapsack-problem-on-caks1000-test</loc><lastmod>2026-05-19T12:02:44.402Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/combinatorial-auction-knapsack-problem-on-caks500-test</loc><lastmod>2026-05-19T12:02:44.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/combinatorial-auction-knapsack-problem-on-caks100-test</loc><lastmod>2026-05-19T12:02:44.320Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-embodied-ai-performance-on-aggregate-sokoban-frozenlake-navigation-primitiveskill</loc><lastmod>2026-05-19T11:52:40.555Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-robotic-manipulation-on-primitiveskill-via-maniskill</loc><lastmod>2026-05-19T11:52:40.468Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-3d-embodied-navigation-on-embodied-3d-navigation</loc><lastmod>2026-05-19T11:52:40.425Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/2d-discrete-grid-world-planning-on-frozenlake</loc><lastmod>2026-05-19T11:52:40.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-language-understanding-on-qwen3-0-6b-evaluation-suite-test</loc><lastmod>2026-05-19T11:38:18.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-humaneval-mbpp-bigcodebench-aggregate</loc><lastmod>2026-05-19T11:23:40.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-bigcodebench-hard</loc><lastmod>2026-05-19T11:23:40.140Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-bigcodebench-full-pass-at-1</loc><lastmod>2026-05-19T11:23:40.104Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-mbpp-base-pass-at-1</loc><lastmod>2026-05-19T11:23:40.075Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-humaneval-base-pass-at-1</loc><lastmod>2026-05-19T11:23:40.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-solar-tailauc-excessauc</loc><lastmod>2026-05-19T11:23:08.134Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-weather-tailauc-excessauc</loc><lastmod>2026-05-19T11:23:08.097Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-etth1-tailauc-excessauc</loc><lastmod>2026-05-19T11:23:08.033Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/segment-intrusion-on-segment-intrusion-restaurant-domain-1-0-test</loc><lastmod>2026-05-19T11:22:31.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/segment-intrusion-on-segment-intrusion-laptop-domain-1-0-test</loc><lastmod>2026-05-19T11:22:31.586Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/article-generation-on-magmar-oracle-leaderboard-snapshot</loc><lastmod>2026-05-19T11:04:30.143Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/combinatorial-optimization-on-euclidean-steiner-test</loc><lastmod>2026-05-19T10:53:53.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ordinal-classification-on-dr</loc><lastmod>2026-05-19T10:22:14.939Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ordinal-classification-on-adience</loc><lastmod>2026-05-19T10:22:14.900Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ordinal-classification-on-dr-official-test</loc><lastmod>2026-05-19T10:22:14.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ordinal-classification-on-adience-official-test</loc><lastmod>2026-05-19T10:22:14.789Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-smac-terran_10v10-v2-test</loc><lastmod>2026-07-07T08:51:22.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-vl-mia-flickr</loc><lastmod>2026-05-19T10:02:07.100Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-vl-mia-flickr-test</loc><lastmod>2026-05-19T10:02:06.953Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-aime-hmmt-and-olympiadbench-aggregate</loc><lastmod>2026-05-19T09:53:37.242Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-accuracy-on-osworld</loc><lastmod>2026-05-19T09:33:53.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-task-accuracy-on-osworld</loc><lastmod>2026-05-19T09:33:53.623Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-reasoning-on-ssv2</loc><lastmod>2026-05-19T09:33:23.336Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concurrency-control-performance-comparison-on-multi-agent-coordination-workload-pg-comparison-full-n-4-8-16-32-64</loc><lastmod>2026-05-19T09:22:47.037Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/nuclear-instance-segmentation-on-monuseg</loc><lastmod>2026-05-19T08:31:36.335Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-zero-shot-classification-on-objaverse-lvis</loc><lastmod>2026-05-19T08:14:29.996Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-quality-assessment-on-in-domain-overall</loc><lastmod>2026-05-19T08:11:56.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-understanding-on-longbench-7-category-performance-summary</loc><lastmod>2026-05-19T08:11:32.255Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-amap-test</loc><lastmod>2026-05-19T08:05:23.140Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-cite-test</loc><lastmod>2026-05-19T08:05:23.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-dblp-test</loc><lastmod>2026-05-19T08:05:23.075Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-acm-test</loc><lastmod>2026-05-19T08:05:23.042Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-encoding-on-twitch</loc><lastmod>2026-05-19T08:01:28.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-encoding-on-ite-8k</loc><lastmod>2026-05-19T08:00:50.815Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-encoding-on-ite-4k</loc><lastmod>2026-05-19T08:00:50.788Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-encoding-on-netflix-chimera</loc><lastmod>2026-05-19T08:00:50.758Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-recovery-on-synthetic-nonlinear-sem-gumbel-noise-test</loc><lastmod>2026-05-19T07:52:15.757Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-recovery-on-synthetic-nonlinear-sem-exponential-noise-test</loc><lastmod>2026-05-19T07:52:15.730Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-recovery-on-synthetic-nonlinear-sem-gaussian-noise-test</loc><lastmod>2026-05-19T07:52:15.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hypergraph-node-classification-on-dblp-ca-50-25-25-test</loc><lastmod>2026-05-19T07:35:34.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/malware-detection-on-windows-pe-files-d3-test</loc><lastmod>2026-05-19T07:31:18.593Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-multimodal-understanding-on-mmbench-video</loc><lastmod>2026-05-19T07:23:25.512Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-reasoning-on-tunnel-vision-babyvision-and-tracer-bench</loc><lastmod>2026-05-19T07:21:15.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-reasoning-on-tracer-bench</loc><lastmod>2026-05-19T07:21:15.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-reasoning-on-babyvision</loc><lastmod>2026-05-19T07:21:15.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-reasoning-on-tunnel-vision</loc><lastmod>2026-05-19T07:21:15.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-vcr</loc><lastmod>2026-05-19T07:21:15.529Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-average-at-16-accuracy</loc><lastmod>2026-05-19T07:11:45.659Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiad-bench-average-at-16-accuracy</loc><lastmod>2026-05-19T07:11:45.630Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-minerva-math-avg-at-16-accuracy</loc><lastmod>2026-05-19T07:11:45.578Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-average-at-16-accuracy</loc><lastmod>2026-05-19T07:11:45.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/real-time-streaming-on-streamingbench</loc><lastmod>2026-05-19T07:11:11.732Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counterfactual-explanations-on-housing</loc><lastmod>2026-05-19T06:48:39.180Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counterfactual-explanations-on-fico</loc><lastmod>2026-05-19T06:48:39.101Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counterfactual-explanations-on-diabetes</loc><lastmod>2026-05-29T11:33:03.691Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counterfactual-explanations-on-cancer</loc><lastmod>2026-05-19T06:48:38.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-attribution-on-fma-large-test</loc><lastmod>2026-05-18T09:20:19.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/field-segmentation-on-ai4smallfarms-vietnam</loc><lastmod>2026-05-18T09:19:49.357Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-structure-generation-on-cameo22-and-atlas-large-400-aa-test</loc><lastmod>2026-05-18T09:18:30.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-structure-generation-on-cameo22-and-atlas-medium-51-400-aa-test</loc><lastmod>2026-05-18T09:18:30.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-structure-generation-on-cameo22-and-atlas-small-50-aa-test</loc><lastmod>2026-05-18T09:18:30.721Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/thermodynamic-property-estimation-on-ising-model-beta-0-50</loc><lastmod>2026-05-18T08:58:35.803Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/thermodynamic-property-estimation-on-ising-model-beta-0-44</loc><lastmod>2026-05-18T08:58:35.773Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physical-property-estimation-on-edwards-anderson-model-beta-0-60</loc><lastmod>2026-05-18T08:58:35.739Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physical-property-estimation-on-edwards-anderson-model-beta-0-30</loc><lastmod>2026-05-18T08:58:35.705Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/thermodynamic-property-estimation-on-ising-model-beta-0-42</loc><lastmod>2026-05-18T08:58:35.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/thermodynamic-property-estimation-on-ising-model-beta-0-40</loc><lastmod>2026-05-18T08:58:35.633Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physical-property-estimation-on-edwards-anderson-model-beta-0-90</loc><lastmod>2026-05-18T08:58:35.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-multimodal-duplication-localization-on-rtm</loc><lastmod>2026-05-18T08:38:53.676Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-bandwidth-extension-on-vctk-english</loc><lastmod>2026-05-18T08:38:15.808Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rough-volatility-modeling-on-rough-volatility-terminal-marginal-results</loc><lastmod>2026-05-18T08:21:11.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-reasoning-on-tvqa-plus</loc><lastmod>2026-05-18T08:18:07.961Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-reasoning-on-online-mmsi</loc><lastmod>2026-05-18T08:18:07.923Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-reasoning-on-mmsi</loc><lastmod>2026-05-18T08:18:07.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-conversational-memory-question-answering-on-locomo-test</loc><lastmod>2026-05-18T08:08:03.398Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-triviaqa-msmarco-nq-open-macro-average</loc><lastmod>2026-05-18T07:47:59.238Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-open-out-of-distribution-test</loc><lastmod>2026-05-18T07:47:59.202Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-msmarco-out-of-distribution-test</loc><lastmod>2026-05-18T07:47:59.156Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-out-of-distribution-test</loc><lastmod>2026-05-18T07:47:59.106Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-in-distribution-test</loc><lastmod>2026-05-18T07:47:59.059Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-attribution-on-fashionmnist</loc><lastmod>2026-05-18T07:28:32.826Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-attribution-on-svhn</loc><lastmod>2026-05-18T07:28:32.783Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-evaluation-on-livebench</loc><lastmod>2026-05-18T07:07:44.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-poisoning-attack-on-fever-k-10-test</loc><lastmod>2026-05-18T06:37:34.388Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/world-model-evaluation-on-world-arena-benchmark</loc><lastmod>2026-05-15T10:01:08.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-unlearning-on-wmdp-cyber-quantization-metrics</loc><lastmod>2026-05-15T09:59:36.850Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-unlearning-on-wmdp-chem</loc><lastmod>2026-05-15T09:59:36.824Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-unlearning-on-wmdp-bio-quantization-metrics</loc><lastmod>2026-05-15T09:59:36.790Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-moment-retrieval-on-activitynet</loc><lastmod>2026-05-15T09:27:11.903Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-interaction-grounding-on-ego-irgbench-val</loc><lastmod>2026-05-15T09:13:01.406Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-interaction-answering-on-ego-irgbench-val</loc><lastmod>2026-05-15T09:13:01.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-interaction-analysis-on-ego-irgbench-val</loc><lastmod>2026-05-15T09:13:01.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-interaction-grounding-on-ego-irgbench-test</loc><lastmod>2026-05-15T09:13:01.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-interaction-answering-on-ego-irgbench-test</loc><lastmod>2026-05-15T09:13:01.245Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-interaction-analysis-on-ego-irgbench-test</loc><lastmod>2026-05-15T09:13:01.211Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-to-image-retrieval-on-cub-200-2011</loc><lastmod>2026-05-15T09:06:26.571Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-generation-on-wiki-exante-test</loc><lastmod>2026-05-15T08:57:02.662Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-qa-exante-test</loc><lastmod>2026-05-15T08:57:02.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-head-mesh-reconstruction-on-d-test</loc><lastmod>2026-05-15T08:48:16.677Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-video-generation-on-vbench-30-seconds</loc><lastmod>2026-06-18T07:50:47.223Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lifelong-safety-adaptation-on-safety-benchmarks-final-day</loc><lastmod>2026-05-15T08:26:52.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-brumo-pass-at-1</loc><lastmod>2026-05-15T08:16:49.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-b-aime-pass-at-1</loc><lastmod>2026-05-15T08:16:49.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/low-light-adverse-weather-restoration-on-lol-snow-v1-test</loc><lastmod>2026-05-15T08:07:51.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/low-light-adverse-weather-restoration-on-lol-raindrop-v1-test</loc><lastmod>2026-05-15T08:07:51.590Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/low-light-adverse-weather-restoration-on-lol-rain-v1-test</loc><lastmod>2026-05-15T08:07:51.563Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/low-light-adverse-weather-restoration-on-lol-fog-v1-test</loc><lastmod>2026-05-15T08:07:51.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-constrained-reinforcement-learning-on-safety-gym-safetypointcircle1-evaluation</loc><lastmod>2026-07-01T06:46:16.985Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-classification-on-speech-commands-v2</loc><lastmod>2026-05-15T07:51:11.362Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-ability-driving-assessment-on-bench2drive-base-set</loc><lastmod>2026-05-15T07:48:39.963Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimedia-forgery-detection-on-openmmsec</loc><lastmod>2026-05-15T07:40:35.293Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-horizon-forecasting-on-stackoverflow</loc><lastmod>2026-05-15T07:36:34.564Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-horizon-forecasting-on-earthquake</loc><lastmod>2026-05-15T07:36:34.529Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-horizon-forecasting-on-taxi</loc><lastmod>2026-05-15T07:35:59.972Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-horizon-forecasting-on-retweet</loc><lastmod>2026-05-15T07:35:59.939Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-multimodal-understanding-on-mmlong</loc><lastmod>2026-05-15T07:33:27.679Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-resolution-visual-understanding-on-hrbench</loc><lastmod>2026-05-15T07:33:27.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-on-aime-2025-acc-amsr</loc><lastmod>2026-05-15T07:04:10.506Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-aime-2024-accuracy-and-amsr</loc><lastmod>2026-05-15T07:04:10.467Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-trec-acc-amsr</loc><lastmod>2026-05-15T07:04:10.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-doc-qa-on-hotpotqa</loc><lastmod>2026-05-15T07:04:10.390Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-acc-amsr</loc><lastmod>2026-05-15T07:04:10.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sinogram-completion-on-tomobank</loc><lastmod>2026-05-15T07:01:38.363Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-retrieval-on-stark-amazon-synthetic-test</loc><lastmod>2026-05-15T06:56:19.366Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/voxelwise-knn-segmentation-on-hcp-t2w-t1w-k-7-dataset-fit</loc><lastmod>2026-05-14T10:00:35.354Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/voxelwise-knn-segmentation-on-abdomen-mr-ct-k-7-dataset-fit</loc><lastmod>2026-05-14T10:00:35.322Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/registration-free-correspondence-on-hcp-t2w-t1w-dataset</loc><lastmod>2026-05-14T10:00:35.290Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/registration-free-correspondence-on-abdomen-mr-ct-dataset-fit-isotropic-voxel-sizes-2-0-2-0-2-0-mm3-held-out</loc><lastmod>2026-05-14T10:00:35.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/part-label-transfer-on-shapenet</loc><lastmod>2026-05-14T09:56:03.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/length-of-stay-prediction-on-eicu-los-test</loc><lastmod>2026-05-14T09:56:02.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/length-of-stay-prediction-on-mimic-iv-los-test</loc><lastmod>2026-05-14T09:56:02.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grammatical-error-correction-on-cweb-g-test</loc><lastmod>2026-05-14T09:45:59.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/discontinuous-constituent-parsing-on-dptb-test</loc><lastmod>2026-05-14T09:15:50.013Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/persuasive-essay-production-against-scientific-consensus-on-scientific-consensus-topics-full-3x3-cross-product-1-0</loc><lastmod>2026-05-14T09:15:48.875Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-germanquad</loc><lastmod>2026-05-14T09:05:54.275Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-wikitext-103-ppl-and-mauve</loc><lastmod>2026-05-14T09:05:54.249Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-germanquad</loc><lastmod>2026-05-14T09:05:54.223Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-codeparrot</loc><lastmod>2026-05-14T09:05:54.196Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-writingprompts-rouge-1</loc><lastmod>2026-05-14T09:05:54.167Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-wikitext-103-rouge-1</loc><lastmod>2026-05-14T09:05:54.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-wikitext-2-rouge-1</loc><lastmod>2026-05-14T09:05:54.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-system-robustness-evaluation-on-gqa-1-0-test</loc><lastmod>2026-05-14T08:57:48.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-recognition-on-ucf101-meta-test</loc><lastmod>2026-05-14T08:56:48.010Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adroit-pen-manipulation-on-odrl-adroit-pen-shrink-finger-medium</loc><lastmod>2026-05-22T08:51:18.961Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adroit-pen-manipulation-on-odrl-adroit-pen-broken-joint-high</loc><lastmod>2026-05-22T08:51:18.931Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adroit-pen-manipulation-on-odrl-adroit-pen-broken-joint-medium</loc><lastmod>2026-05-22T08:51:18.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-multimodal-multiple-choice-question-answering-on-afri-mcqa</loc><lastmod>2026-05-14T07:55:21.988Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/neural-operator-learning-on-2d-burgers</loc><lastmod>2026-05-14T07:35:14.364Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-question-answering-on-sciknoweval</loc><lastmod>2026-07-03T06:32:21.355Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-on-pmc</loc><lastmod>2026-05-14T06:55:01.665Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-lingual-cultural-consistency-on-blend-non-indo-european</loc><lastmod>2026-05-14T06:55:00.299Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-lingual-cultural-consistency-on-blend-indo-european</loc><lastmod>2026-05-14T06:55:00.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-lingual-cultural-consistency-on-blend-lower-resource</loc><lastmod>2026-05-14T06:55:00.227Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-lingual-cultural-consistency-on-blend-higher-resource</loc><lastmod>2026-05-14T06:55:00.192Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-lingual-cultural-consistency-on-blend-all-8-languages</loc><lastmod>2026-05-14T06:55:00.154Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logic-puzzles-on-k-and-k-logic-puzzles</loc><lastmod>2026-05-14T06:45:50.808Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-based-grounding-on-webeyes-test</loc><lastmod>2026-05-13T11:34:51.332Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ranking-on-argkp-21</loc><lastmod>2026-05-13T11:25:47.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empirical-coverage-estimation-on-riverswim-episode-length-t-100</loc><lastmod>2026-05-13T11:15:42.153Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empirical-coverage-estimation-on-riverswim-t-100-50-percent-coverage</loc><lastmod>2026-05-13T11:15:42.049Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/state-value-coverage-estimation-on-riverswim-t-100</loc><lastmod>2026-05-13T11:15:41.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/action-value-coverage-estimation-on-riverswim-t-100</loc><lastmod>2026-05-13T11:15:41.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-mmlu-gsm8k</loc><lastmod>2026-05-13T10:54:38.829Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-classification-a-v-on-vggsound-avel-90k</loc><lastmod>2026-05-13T10:37:18.989Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-classification-v-a-on-vggsound-avel-40k</loc><lastmod>2026-05-13T10:37:18.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/subject-consistent-image-generation-on-omnicontext</loc><lastmod>2026-06-26T08:47:57.388Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-agent-memory-evaluation-on-longmemeval</loc><lastmod>2026-05-13T10:18:06.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-cfp-fp</loc><lastmod>2026-05-13T10:14:26.501Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-cfp-ff</loc><lastmod>2026-05-13T10:14:26.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-scface-far</loc><lastmod>2026-05-13T10:14:26.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-scface-medium</loc><lastmod>2026-05-13T10:14:26.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-scface-close</loc><lastmod>2026-05-13T10:14:26.366Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-arface-scarf</loc><lastmod>2026-05-13T10:14:26.333Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-arface-glass</loc><lastmod>2026-05-13T10:14:26.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/face-recognition-attribution-on-arface-neutral</loc><lastmod>2026-05-13T10:14:26.267Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-consistency-rate-overconfidence-rate</loc><lastmod>2026-05-13T10:08:29.492Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-squad-v2-accuracy-consistency-overconfidence</loc><lastmod>2026-05-13T10:08:29.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-sst2-accuracy-consistency-rate-overconfidence-rate</loc><lastmod>2026-05-13T10:08:29.370Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-vectorization-on-div2k-1-0-train</loc><lastmod>2026-05-13T10:04:21.649Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chat-quality-assessment-on-mt-bench-ultrachat</loc><lastmod>2026-05-13T09:54:19.410Z</lastmod></url></urlset>