<?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/hallucination-detection-on-dolly-llama2-13b-test</loc><lastmod>2026-02-26T05:31:11.800Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-ragtruth-llama2-13b-test</loc><lastmod>2026-02-26T05:26:46.075Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-dolly-llama2-7b-test</loc><lastmod>2026-02-26T05:26:46.039Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-ragtruth-llama2-7b-test</loc><lastmod>2026-02-26T05:31:11.781Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-100-question-subset-test</loc><lastmod>2026-04-07T08:32:07.526Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/viewpoint-classification-on-immigration-3k</loc><lastmod>2026-02-26T05:43:33.706Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-retrieval-on-mteb-code</loc><lastmod>2026-05-14T09:32:14.394Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-general-capability</loc><lastmod>2026-02-26T05:38:56.198Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-hh-rlhf-test</loc><lastmod>2026-02-26T05:46:22.675Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-spelling-check-on-lemon-cscd-ns-and-cs-combined</loc><lastmod>2026-02-26T05:35:24.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-spelling-check-on-cs</loc><lastmod>2026-02-26T06:04:16.689Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-spelling-check-on-lemon</loc><lastmod>2026-02-26T05:38:03.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-classification-on-eurlex</loc><lastmod>2026-05-19T08:28:41.645Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-include-base-44</loc><lastmod>2026-02-26T05:35:51.044Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-mlc-slm-dev</loc><lastmod>2026-06-11T07:42:01.118Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-tracing-on-ednet-500-test</loc><lastmod>2026-02-26T05:24:53.047Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-tracing-on-dbe-kt22-test</loc><lastmod>2026-02-26T05:24:53.030Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fairness-on-dermobench-fairness</loc><lastmod>2026-02-26T05:45:09.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-dermobench-reasoning</loc><lastmod>2026-02-26T06:05:50.013Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnosis-on-dermobench-out-of-distribution</loc><lastmod>2026-02-26T05:40:44.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diagnosis-on-dermobench-in-distribution</loc><lastmod>2026-02-26T05:34:01.956Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/morphology-on-dermobench-morphology</loc><lastmod>2026-02-26T06:05:49.620Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-agent-on-swe-bench-verified</loc><lastmod>2026-07-02T08:11:11.251Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/script-confusion-mitigation-on-fleurs-zh-trad-test</loc><lastmod>2026-02-26T05:31:05.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/script-confusion-mitigation-on-fleurs-zh-sim-test</loc><lastmod>2026-02-26T05:53:42.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/script-confusion-mitigation-on-fleurs-sr-cyrl-test</loc><lastmod>2026-02-26T05:53:42.779Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/script-confusion-mitigation-on-fleurs-sr-latn-test</loc><lastmod>2026-02-26T05:34:21.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factuality-evaluation-on-held-out-dataset</loc><lastmod>2026-02-26T05:45:08.659Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-mmlu-en</loc><lastmod>2026-03-06T09:09:01.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-and-avg-gain</loc><lastmod>2026-02-26T05:31:04.524Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-accuracy-and-avg-gain</loc><lastmod>2026-02-26T05:31:04.510Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-tydiqagp</loc><lastmod>2026-02-26T05:45:08.009Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-coqa-factual-accuracy</loc><lastmod>2026-02-26T05:45:07.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-factual-accuracy</loc><lastmod>2026-02-26T05:45:07.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-factual-accuracy</loc><lastmod>2026-02-26T05:45:07.780Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-perf-cost-reward</loc><lastmod>2026-02-26T05:57:47.352Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pre-training-data-detection-on-wikimia-original-length-32</loc><lastmod>2026-02-26T05:26:06.866Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-avg-at-10</loc><lastmod>2026-02-26T05:36:30.417Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-avg-at-10</loc><lastmod>2026-02-26T05:36:30.364Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-avg-at-10</loc><lastmod>2026-02-26T05:36:30.400Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-evaluation-on-kmmlu-kmmlu-pro-gpqa-diamond-and-related-benchmarks</loc><lastmod>2026-02-26T05:31:01.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sql-execution-performance-on-bird-n-1534</loc><lastmod>2026-02-26T05:41:42.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-svamp-accuracy</loc><lastmod>2026-02-26T05:30:58.886Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-answerable-setting</loc><lastmod>2026-02-26T05:39:44.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-distractor-setting</loc><lastmod>2026-02-26T05:39:44.822Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-train</loc><lastmod>2026-02-26T05:30:58.672Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-deepfake-detection-on-celeb-df-cdf</loc><lastmod>2026-02-26T06:08:16.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-en-multifield</loc><lastmod>2026-02-27T10:44:56.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-multinews-rouge-l</loc><lastmod>2026-02-27T10:44:57.318Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-aggregate-suite-alpaca-codealpaca-humaneval-livecodebench-math500-mbpp-mt-bench</loc><lastmod>2026-02-26T05:52:24.133Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-mbpp</loc><lastmod>2026-02-26T06:04:41.486Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-speedup-on-math500</loc><lastmod>2026-02-26T06:04:41.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-livecodebench</loc><lastmod>2026-02-26T06:04:41.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-mmlu-o-1-semantic-level</loc><lastmod>2026-02-26T05:30:57.560Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-o-1-domain-level-split</loc><lastmod>2026-02-26T05:30:57.525Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-o-1-semantic-level</loc><lastmod>2026-02-26T05:30:57.513Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-o-1-exact-split</loc><lastmod>2026-02-26T05:30:57.497Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multitask-language-understanding-on-mmlu-semantic-level-split-o-3</loc><lastmod>2026-02-26T05:30:57.479Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-domain-level-split-o-3</loc><lastmod>2026-02-26T05:30:57.444Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-semantic-level-split-o-3</loc><lastmod>2026-02-26T05:30:57.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-exact-split-o-3</loc><lastmod>2026-02-26T05:30:57.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-ls-clean</loc><lastmod>2026-06-11T06:37:09.409Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-wenetspeech-chuan-hard</loc><lastmod>2026-04-21T12:37:51.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-wenetspeech-chuan-easy</loc><lastmod>2026-04-21T12:37:51.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-retrieval-on-beir-15</loc><lastmod>2026-02-26T05:53:05.398Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-heval</loc><lastmod>2026-06-17T07:50:24.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-task-performance-on-macro-average-mathematics-multi-hop-qa-code-generation</loc><lastmod>2026-02-26T05:30:56.054Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-code-generation</loc><lastmod>2026-02-26T05:30:56.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-evaluation-on-mmlu-pro-law-test</loc><lastmod>2026-02-26T05:46:08.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-defense-on-jailbreakbench-and-advbench</loc><lastmod>2026-02-26T05:23:51.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-diamond-p-at-1-p-at-16</loc><lastmod>2026-02-26T05:54:47.093Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-question-answering-on-python-code-question-answering-downstream</loc><lastmod>2026-02-26T05:30:54.007Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-completion-on-python-code-completion-downstream</loc><lastmod>2026-02-26T05:42:32.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-editing-on-evk-bench</loc><lastmod>2026-02-26T05:41:58.056Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimization-modeling-on-complexor</loc><lastmod>2026-05-29T10:14:18.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-understanding-on-ruler-16k-context-length</loc><lastmod>2026-05-13T09:31:06.449Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-hle</loc><lastmod>2026-02-26T05:32:03.108Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-language-understanding-on-mmmlu-massive-multilingual-language-understanding</loc><lastmod>2026-02-26T05:32:35.940Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-average-squad-newsqa-triviaqa-nq-hotpotqa</loc><lastmod>2026-02-26T05:45:09.910Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-faith-and-accuracy</loc><lastmod>2026-02-26T05:45:10.521Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-faith-accuracy</loc><lastmod>2026-02-26T05:45:09.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-faith-and-accuracy</loc><lastmod>2026-02-26T05:45:09.871Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-squad-faith-acc</loc><lastmod>2026-02-26T05:45:10.504Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-reasoning-on-piqa-hellaswag-arc-e-arc-c-obqa-race-wsc273-lambada-mmlu</loc><lastmod>2026-02-26T05:55:04.326Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sop-understanding-on-sopbench-test</loc><lastmod>2026-02-26T05:37:37.050Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-text-to-sql-on-epiaskkb-2025-test</loc><lastmod>2026-02-26T05:30:49.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-beyond-aime</loc><lastmod>2026-02-26T05:57:27.909Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unsafe-content-detection-on-llavaguard</loc><lastmod>2026-07-02T08:40:59.568Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-bin-packing-problem-on-offline-bpp</loc><lastmod>2026-02-26T05:54:11.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/capacitated-vehicle-routing-problem-on-cvrp-objective-value</loc><lastmod>2026-02-26T05:54:11.933Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traveling-salesman-problem-on-tsp-objective-value</loc><lastmod>2026-02-26T05:54:11.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-etth2-ettm1-test</loc><lastmod>2026-04-15T09:30:57.634Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-arm-manipulation-on-metaworld-very-hard</loc><lastmod>2026-05-13T10:39:20.322Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medxpert-test</loc><lastmod>2026-06-26T08:26:15.504Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-dimensional-knapsack-problem-on-mkp-n-100-m-5</loc><lastmod>2026-02-26T05:54:11.305Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/content-moderation-on-aegis-2-0</loc><lastmod>2026-04-07T08:47:16.706Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chemical-reaction-prediction-on-uspto50k</loc><lastmod>2026-03-04T17:09:37.303Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-and-general-reasoning-on-gpqa-diamond</loc><lastmod>2026-02-26T05:57:30.514Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-and-general-reasoning-on-mmlu-pro</loc><lastmod>2026-02-26T05:57:30.496Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-gsm8k-pass-at-1</loc><lastmod>2026-02-26T05:57:23.378Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-manipulation-on-libero-openvla-oft</loc><lastmod>2026-03-31T10:03:08.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-question-answering-on-nq-natural-questions-test</loc><lastmod>2026-02-26T05:33:32.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/job-shop-scheduling-problem-on-jssp</loc><lastmod>2026-02-26T05:45:12.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/minimum-vertex-cover-on-mvc</loc><lastmod>2026-02-26T05:45:12.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/maximum-independent-set-on-mis</loc><lastmod>2026-02-26T05:45:12.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/capacitated-vehicle-routing-problem-on-cvrp</loc><lastmod>2026-02-26T05:45:12.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/orienteering-problem-on-op</loc><lastmod>2026-02-26T05:45:12.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traveling-salesperson-problem-on-tsp</loc><lastmod>2026-02-26T05:45:12.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-robustness-on-gcg</loc><lastmod>2026-02-26T05:45:40.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-on-wildjailbreak</loc><lastmod>2026-02-26T05:46:23.154Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-agentic-on-pddl</loc><lastmod>2026-02-26T05:27:32.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-agentic-on-gaia</loc><lastmod>2026-02-26T05:27:32.733Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-agentic-on-sciworld</loc><lastmod>2026-02-26T05:27:32.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-hate-speech-detection-on-mmhs11k-test</loc><lastmod>2026-02-26T05:30:42.921Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-erd-s-minimum-overlap-problem</loc><lastmod>2026-06-12T08:25:05.240Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binding-affinity-prediction-on-casf-2016-test</loc><lastmod>2026-06-23T10:32:35.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sycophancy-on-faithfulqa</loc><lastmod>2026-02-26T06:05:47.380Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/refusal-on-saladbench</loc><lastmod>2026-02-26T06:03:49.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-reasoning-domain-game</loc><lastmod>2026-02-26T06:03:49.179Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-reasoning-domain-logic</loc><lastmod>2026-02-26T06:03:49.163Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-reasoning-domain-arithmetic</loc><lastmod>2026-02-26T06:03:49.146Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-reasoning-domain-social</loc><lastmod>2026-02-26T06:03:49.129Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-reasoning-domain-code</loc><lastmod>2026-02-26T06:01:10.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-wtq</loc><lastmod>2026-03-18T08:23:51.082Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/masked-entity-prediction-on-icews05-15-standard-test</loc><lastmod>2026-02-26T05:50:27.105Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/masked-entity-prediction-on-icews18-standard-test</loc><lastmod>2026-02-26T05:50:27.091Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-discipline-reasoning-on-mmmu-pro</loc><lastmod>2026-03-16T09:30:17.882Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-mmlu-pro-test</loc><lastmod>2026-03-04T11:49:56.330Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/communication-overhead-on-tinyimagenet-test</loc><lastmod>2026-02-26T06:07:55.318Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/communication-overhead-on-cifar-100-test</loc><lastmod>2026-02-26T06:07:55.302Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/communication-overhead-on-cifar-10-test</loc><lastmod>2026-02-26T06:07:55.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-label-classification-on-chexpert-roc-auc</loc><lastmod>2026-02-26T06:00:22.938Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-grounded-reasoning-on-hr-bench-8k</loc><lastmod>2026-03-06T07:08:26.756Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-grounded-reasoning-on-hr-bench-4k</loc><lastmod>2026-03-06T07:08:26.727Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/skeleton-based-action-recognition-on-ntu-rgb-plus-d-x-sub</loc><lastmod>2026-02-26T05:30:39.389Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-retrieval-image-query-on-webqa</loc><lastmod>2026-02-27T10:33:15.820Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-retrieval-text-query-on-webqa</loc><lastmod>2026-02-27T10:33:15.788Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-retrieval-image-query-on-mmqa</loc><lastmod>2026-02-27T10:33:15.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-retrieval-text-query-on-mmqa</loc><lastmod>2026-02-27T10:33:15.720Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-label-content-safety-classification-on-synthetic-dataset</loc><lastmod>2026-02-26T05:43:28.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ocr-based-visual-question-answering-on-ai2d-2016-test</loc><lastmod>2026-02-26T05:30:38.082Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-dbpedia-beir-test</loc><lastmod>2026-04-13T10:11:11.523Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-clustering-on-aggregate</loc><lastmod>2026-02-26T05:51:33.756Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-clustering-on-yah-b</loc><lastmod>2026-02-26T05:30:37.196Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-clustering-on-yah-f</loc><lastmod>2026-02-26T05:30:37.180Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-image-understanding-on-muirbench-test</loc><lastmod>2026-02-26T05:31:37.792Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-commonsense-reasoning-on-m-hellaswag</loc><lastmod>2026-02-26T05:34:34.504Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toxicity-detection-on-hatexplain</loc><lastmod>2026-02-26T05:24:52.275Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-argument-extraction-on-ace-2005</loc><lastmod>2026-04-14T09:45:09.954Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-qa-on-coverage-test</loc><lastmod>2026-02-26T05:58:29.227Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-coverage-test</loc><lastmod>2026-02-26T05:58:29.211Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-coverage-test</loc><lastmod>2026-02-26T05:58:29.195Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-coverage-dataset-test</loc><lastmod>2026-02-26T05:58:29.177Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-editing-on-counterfact-full-test</loc><lastmod>2026-02-26T06:01:51.282Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-editing-on-zsre-evaluation</loc><lastmod>2026-02-26T06:02:05.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-iirc</loc><lastmod>2026-07-03T08:03:08.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cddb-hard-test</loc><lastmod>2026-02-26T05:30:33.979Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-captioning-on-mscoco-random-sampling-of-500-instances</loc><lastmod>2026-02-26T05:38:20.047Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-december-2018-wikipedia-dump-test</loc><lastmod>2026-06-26T07:23:26.836Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-triviaqa-and-webq-test</loc><lastmod>2026-02-26T05:30:33.655Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-longbench-v1-test</loc><lastmod>2026-02-26T06:02:50.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-alpaca-test</loc><lastmod>2026-04-30T06:34:18.444Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-view-synthesis-on-nerf-synthetic-800-x-800-test</loc><lastmod>2026-02-26T05:56:24.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-view-synthesis-on-real-forward-facing-640-x-960-test</loc><lastmod>2026-02-26T05:56:24.928Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-understanding-reasoning-on-mlvu</loc><lastmod>2026-04-10T09:12:01.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reading-comprehension-on-race-middle-and-high-difficulty-scores</loc><lastmod>2026-06-04T11:58:17.794Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-generation-on-longbench-write-en-binned-context-length-metrics</loc><lastmod>2026-06-09T11:23:58.190Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-denoising-on-cbsd68-sigma-50</loc><lastmod>2026-02-26T05:56:46.074Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-denoising-on-cbsd68-sigma-25</loc><lastmod>2026-02-26T05:56:46.055Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-denoising-on-cbsd68-sigma-15</loc><lastmod>2026-02-26T05:56:46.036Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-defense-on-aggregate-benchmarks</loc><lastmod>2026-02-26T05:46:23.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-defense-on-gptfuzzer</loc><lastmod>2026-02-26T05:46:23.341Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-defense-on-renellm-and-deepinception-average</loc><lastmod>2026-02-26T05:46:23.325Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fingerprint-verification-on-wizardmath-7b-v1-0</loc><lastmod>2026-02-26T06:08:05.008Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-question-answering-on-deve-qa-test</loc><lastmod>2026-02-26T05:34:24.240Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-text-compositionality-evaluation-on-sugarcrepe-plus-plus-test</loc><lastmod>2026-03-27T15:32:45.846Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-visulogic</loc><lastmod>2026-06-09T06:35:32.480Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-super-resolution-on-reds</loc><lastmod>2026-02-26T05:57:09.732Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-evaluation-on-stableeval-27-evals</loc><lastmod>2026-02-26T05:35:33.017Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-scene-centric-datasets</loc><lastmod>2026-02-26T05:30:30.432Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-object-centric-datasets</loc><lastmod>2026-02-26T05:30:30.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/super-resolution-on-hggt-test-100</loc><lastmod>2026-02-26T05:51:20.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stereo-matching-on-middlebury-full-resolution</loc><lastmod>2026-04-23T10:44:48.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/citation-augmented-question-answering-on-gt-pk-1-0-test</loc><lastmod>2026-02-27T10:26:11.291Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-forecasting-on-etth1-t-96</loc><lastmod>2026-06-01T09:31:04.541Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-alignment-on-xstest</loc><lastmod>2026-05-12T08:44:59.183Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-reconstruction-on-panda-70m</loc><lastmod>2026-04-21T07:25:09.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/person-re-identification-on-ltcc-clothing-change-test</loc><lastmod>2026-02-26T06:06:50.609Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-en-ru-document-level</loc><lastmod>2026-03-27T14:18:21.886Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-ettm1-zero-shot-transfer-from-etth1</loc><lastmod>2026-04-15T09:30:57.583Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-action-recognition-on-hmdb-5-way-k-shot-evaluation</loc><lastmod>2026-02-26T05:33:14.003Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-attack-on-stl10</loc><lastmod>2026-03-31T11:17:48.078Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/perception-evaluation-on-mme-perception</loc><lastmod>2026-03-25T13:36:56.232Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/implicit-image-representation-on-div2k-train-test</loc><lastmod>2026-02-26T06:04:21.154Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cardiac-ultrasound-segmentation-on-cardiacuda-test</loc><lastmod>2026-02-26T05:40:26.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-classification-on-mtd-test</loc><lastmod>2026-02-26T05:53:23.739Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-erasure-on-cub-test</loc><lastmod>2026-02-26T05:34:42.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-erasure-on-oxford-flowers-test</loc><lastmod>2026-02-26T05:34:42.848Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-erasure-on-stanford-dogs-test</loc><lastmod>2026-02-26T05:34:42.831Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-compositionality-on-sugarcrepe-test</loc><lastmod>2026-02-26T06:02:07.131Z</lastmod></url></urlset>