<?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-lawbench-open-ended-tasks</loc><lastmod>2026-06-09T09:23:51.121Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mmse-score-prediction-on-adni-study-2-multi-modal-study-test</loc><lastmod>2026-06-09T09:17:03.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mmse-score-prediction-on-adni-study-1-heterogeneous-sources-test</loc><lastmod>2026-06-09T09:17:03.597Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-driving-on-longest6-v2</loc><lastmod>2026-06-09T09:17:03.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-spatial-reasoning-on-vla-3d-target-never-directly-observed-n-10</loc><lastmod>2026-06-09T09:14:00.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-spatial-reasoning-on-vla-3d-target-observed-by-vision</loc><lastmod>2026-06-09T09:14:00.209Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-manipulation-on-aloha-agilex-bimanual-platform-real-world-demonstrations</loc><lastmod>2026-06-09T09:13:49.379Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-11-task-average-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.214Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-blocks_ranking_rgb-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.178Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-place_bread_skillet-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.137Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-stack_blocks_two-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.108Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-stack_bowls_three-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.076Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-open_microwave-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-place_cans_plasticbox-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:49.006Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-pick_dual_bottles-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:48.973Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-place_burger_fries-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:48.941Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-beat_block_hammer-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:48.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-coordination-handover_block-on-robotwin-2-0</loc><lastmod>2026-06-09T09:13:48.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-improvement-of-language-agents-on-ds-1000-streambench-32-held-out-episodes</loc><lastmod>2026-06-09T09:13:48.705Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-continuous-improvement-on-cosql-streambench-32-held-out-episodes</loc><lastmod>2026-06-09T09:13:48.661Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scene-graph-generation-on-scenefun3d</loc><lastmod>2026-06-09T09:13:48.615Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/maritime-trajectory-and-destination-forecasting-on-maritime-rlvr-test</loc><lastmod>2026-06-09T09:13:47.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/author-name-disambiguation-on-aminer-google-scholar-2024-2026-test</loc><lastmod>2026-06-09T09:13:47.464Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-on-mixed-1m</loc><lastmod>2026-06-09T09:03:44.645Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2b-test</loc><lastmod>2026-06-09T09:03:44.568Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/eeg-denoising-on-bci-competition-iv-2a-test</loc><lastmod>2026-06-09T09:03:44.535Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detection-of-quotation-errors-on-nealsmith-full</loc><lastmod>2026-06-09T09:03:44.214Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-captioning-on-evc-msvd-clipscores-refclip-s</loc><lastmod>2026-06-09T08:59:18.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/landslide-detection-on-landslide4sense-ood-test</loc><lastmod>2026-06-09T08:55:15.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequence-prediction-on-wikitext-2-average</loc><lastmod>2026-06-09T08:55:15.337Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speaker-diarization-on-voxconverse-test</loc><lastmod>2026-06-24T08:35:17.173Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-explanation-generation-on-gemma-2-27b-sae-gemmascope-res-131k-layer-2</loc><lastmod>2026-06-09T08:50:09.006Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-explanation-generation-on-gemma-2-27b-sae-gemmascope-res-131k-layer-1</loc><lastmod>2026-06-09T08:50:08.982Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-explanation-generation-on-llama-3-1-8b-sae-llamascope-res-32k-layer-2</loc><lastmod>2026-06-09T08:50:08.960Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-explanation-generation-on-llama3-1-8b-sae-llamascope-res-32k-layer-1</loc><lastmod>2026-06-09T08:50:08.931Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-explanation-generation-on-gemma-2-9b-sae-gemmascope-res-16k-layer-2</loc><lastmod>2026-06-09T08:50:08.898Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/feature-explanation-generation-on-gemma-2-9b-sae-gemmascope-res-16k-layer-1</loc><lastmod>2026-06-09T08:50:08.870Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generative-recommendation-on-e-commerce-dataset-test</loc><lastmod>2026-06-09T08:46:36.938Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-calibration-on-pubmed</loc><lastmod>2026-06-09T08:45:36.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-calibration-on-coraml</loc><lastmod>2026-06-09T08:45:36.452Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-calibration-on-cora-ece</loc><lastmod>2026-06-09T08:45:36.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/activity-and-object-prediction-on-homer-plus-test</loc><lastmod>2026-06-09T08:44:32.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/expert-grounded-reasoning-alignment-on-d2-n-499</loc><lastmod>2026-06-09T08:44:32.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-alignment-on-medthink-d2-n-499-test</loc><lastmod>2026-06-09T08:44:32.402Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-alignment-on-medqa-d1-n-500-test</loc><lastmod>2026-06-09T08:44:32.352Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-reconstruction-on-graspnet-1b-1-0-test</loc><lastmod>2026-06-09T08:33:59.556Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/forced-choice-visual-question-answering-on-semantic-stress-evaluation-set</loc><lastmod>2026-06-09T08:33:33.359Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-consistency-evaluation-on-semantic-stress-diagnostic-dataset-evaluation-subset</loc><lastmod>2026-06-09T08:33:33.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-stress-evaluation-on-s3e</loc><lastmod>2026-06-09T08:33:33.279Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-understanding-on-longbench-qasper-qmsum-multiqa-trec-multinews-vcsum</loc><lastmod>2026-06-09T08:33:33.160Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-data-reconstruction-scoring-on-nist-arizona-census-qi2-1940</loc><lastmod>2026-06-09T08:26:25.255Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-data-reconstruction-scoring-on-nist-arizona-census-qi1-1940</loc><lastmod>2026-06-09T08:26:25.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-tabddpm-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:25.087Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-arf-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:25.056Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-ctgan-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:25.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-tvae-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:25.013Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-synthpop-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.982Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-rankswap-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.956Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-cell-suppression-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.928Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-mst-1000-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-mst-100-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.882Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-mst-10-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.858Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-mst-1-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.832Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reconstruction-attack-on-nist-sbo-mst-0-1-qi1-1k-rows</loc><lastmod>2026-06-09T08:26:24.804Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenette-2</loc><lastmod>2026-06-09T08:23:30.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-quantification-in-visual-question-answering-on-advqa</loc><lastmod>2026-06-09T08:23:28.681Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-quantification-in-visual-question-answering-on-okvqa</loc><lastmod>2026-06-09T08:23:28.636Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-quantification-in-visual-question-answering-on-vqa-v2</loc><lastmod>2026-06-09T08:23:28.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-uploaded-respiratory-sound-dataset-test</loc><lastmod>2026-06-09T08:14:15.043Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-action-inference-performance-on-robotwin-2-0</loc><lastmod>2026-06-09T08:14:14.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/state-microstructure-modeling-on-synthetic-r-t-0-space-dataset-test</loc><lastmod>2026-06-09T08:13:44.817Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/omission-detectability-analysis-on-proof-of-solvency-omission-detection-n-10-7-k-100-1-0</loc><lastmod>2026-06-09T08:13:26.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stuttering-detection-on-uclass</loc><lastmod>2026-06-09T08:13:26.807Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/location-estimation-on-oxford-robotcar-overall</loc><lastmod>2026-06-09T08:13:26.607Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/location-estimation-on-oxford-robotcar-test</loc><lastmod>2026-06-09T08:13:26.559Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autoencoding-on-bookcorpus</loc><lastmod>2026-06-09T08:13:25.986Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autoencoding-on-wmt-14</loc><lastmod>2026-06-09T08:13:25.936Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-manipulation-on-robot-manipulation-tasks-out-of-domain</loc><lastmod>2026-06-09T08:13:25.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-structure-generation-on-geometries-2000</loc><lastmod>2026-06-09T08:07:40.419Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-manipulation-on-vr-gps-9-objects-test</loc><lastmod>2026-06-09T08:03:32.091Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-stability-change-prediction-on-s8754</loc><lastmod>2026-06-09T08:03:22.888Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-stability-change-prediction-on-s2648</loc><lastmod>2026-06-09T08:03:22.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-stability-change-prediction-on-s783</loc><lastmod>2026-06-09T08:03:22.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-stability-change-prediction-on-s461</loc><lastmod>2026-06-09T08:03:22.786Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-mmlu-pro-non-trivial-subset-all-14-subjects-test</loc><lastmod>2026-06-09T08:03:22.709Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-smu-text-6</loc><lastmod>2026-06-09T08:03:22.633Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-smu-text-5</loc><lastmod>2026-06-09T08:03:22.600Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-smu-text-4</loc><lastmod>2026-06-09T08:03:22.566Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-smu-text-3</loc><lastmod>2026-06-09T08:03:22.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-smu-text-2</loc><lastmod>2026-06-09T08:03:22.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-smu-text-1</loc><lastmod>2026-06-09T08:03:22.460Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-nmle-2024</loc><lastmod>2026-06-09T08:03:22.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-nmle-2023</loc><lastmod>2026-06-09T08:03:22.395Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-nmle-2022</loc><lastmod>2026-06-09T08:03:22.360Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-usmle-3</loc><lastmod>2026-06-09T08:03:22.324Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-usmle-2</loc><lastmod>2026-06-09T08:03:22.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathology-question-answering-on-usmle-1</loc><lastmod>2026-06-09T08:03:22.245Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-llm-as-a-judge-on-mmlu-prox</loc><lastmod>2026-06-09T08:03:21.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-llm-as-a-judge-on-belebele</loc><lastmod>2026-06-09T08:03:21.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-llm-as-a-judge-on-xstorycloze</loc><lastmod>2026-06-09T08:03:21.390Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-llm-as-a-judge-on-wino-x-mt</loc><lastmod>2026-06-09T08:03:21.354Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-llm-as-a-judge-on-wino-x</loc><lastmod>2026-06-09T08:03:21.314Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-llm-as-a-judge-on-xcopa</loc><lastmod>2026-06-09T08:03:21.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-focused-forecasting-on-jurong-port-after-task-6</loc><lastmod>2026-06-09T07:46:20.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-focused-forecasting-on-jurong-port-after-task-5</loc><lastmod>2026-06-09T07:46:20.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-focused-forecasting-on-jurong-port-after-task-4</loc><lastmod>2026-06-09T07:46:20.502Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-focused-forecasting-on-jurong-port-after-task-3</loc><lastmod>2026-06-09T07:46:20.478Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-focused-forecasting-on-jurong-port-after-task-2</loc><lastmod>2026-06-09T07:46:20.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-focused-forecasting-on-jurong-port-after-task-1</loc><lastmod>2026-06-09T07:46:20.430Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-control-on-d4rl-walker-medium-replay</loc><lastmod>2026-06-09T07:43:15.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-control-on-d4rl-halfcheetah-medium-replay</loc><lastmod>2026-06-09T07:43:15.151Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-control-on-d4rl-walker-medium-expert</loc><lastmod>2026-06-09T07:43:15.112Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-control-on-d4rl-hopper-medium-expert</loc><lastmod>2026-06-09T07:43:15.074Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continuous-control-on-d4rl-halfcheetah-medium-expert</loc><lastmod>2026-06-09T07:43:15.029Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-navix-dynobs16x16-test</loc><lastmod>2026-06-09T07:43:14.989Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-navix-empty16x16-test</loc><lastmod>2026-06-09T07:43:14.951Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-navix-lavagaps7-test</loc><lastmod>2026-06-09T07:43:14.915Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-navix-dynobs6x6-random-test</loc><lastmod>2026-06-09T07:43:14.880Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-navix-crossingss11n5-test</loc><lastmod>2026-06-09T07:43:14.844Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-navix-doorkey8x8-test</loc><lastmod>2026-06-09T07:43:14.806Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-naturalness-evaluation-on-synthesized-speech-samples</loc><lastmod>2026-06-09T07:36:44.594Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-segmentation-on-acdc-test</loc><lastmod>2026-06-09T07:35:13.540Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-segmentation-on-refuge-test</loc><lastmod>2026-06-09T07:35:13.513Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knn-classification-on-tinyimagenet-val</loc><lastmod>2026-06-09T07:33:11.736Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knn-classification-on-imagenet-100-standard-val</loc><lastmod>2026-06-09T07:33:11.689Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knn-classification-on-cifar-10-standard-test</loc><lastmod>2026-06-09T07:33:11.644Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/2-class-hate-speech-classification-on-turkish-hate-speech</loc><lastmod>2026-06-09T07:33:11.497Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-ownership-verification-on-flowers102-and-sdogs120-transfer-reuse</loc><lastmod>2026-06-09T07:33:11.432Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-load-forecasting-on-ut-austin-48h-forecast-horizon-test</loc><lastmod>2026-06-09T07:33:10.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-load-forecasting-on-ut-austin-dataset-24h-forecast-horizon-test</loc><lastmod>2026-06-09T07:33:10.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-load-forecasting-on-ut-austin-dataset-12h-forecast-horizon-test</loc><lastmod>2026-06-09T07:33:10.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-load-forecasting-on-ut-austin-dataset-6h-forecast-horizon-test</loc><lastmod>2026-06-09T07:33:10.593Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multivariate-load-forecasting-on-ut-austin-1h-forecast-horizon-test</loc><lastmod>2026-06-09T07:33:10.563Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/nn-search-on-sift-accuracy</loc><lastmod>2026-06-09T07:33:09.698Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/nn-search-on-hypersphere</loc><lastmod>2026-06-09T07:33:09.661Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/certainty-distortion-evaluation-on-mimic-document-level</loc><lastmod>2026-06-09T07:14:00.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/certainty-distortion-evaluation-on-academic-papers-document-level</loc><lastmod>2026-06-09T07:14:00.784Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overall-certainty-distortion-analysis-on-spiced-and-mimic</loc><lastmod>2026-06-09T07:14:00.752Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrasing-and-simplification-of-radiological-findings-on-mimic</loc><lastmod>2026-06-09T07:14:00.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrasing-and-rewriting-of-scientific-findings-on-spiced</loc><lastmod>2026-06-09T07:14:00.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-social-simulation-on-kindergarten-scenario-30-agents</loc><lastmod>2026-06-09T07:13:05.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-social-simulation-on-kindergarten-scenario-15-agents</loc><lastmod>2026-06-09T07:13:05.845Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-social-simulation-on-kindergarten-scenario-5-agents</loc><lastmod>2026-06-09T07:13:05.816Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/eeg-classification-on-real-eeg-covariance-spd-22-27-subject-split-pairs</loc><lastmod>2026-06-09T07:13:05.406Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geometric-alignment-on-real-eeg-covariance-spd-22-27-subject-split-pairs</loc><lastmod>2026-06-09T07:13:05.367Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-classification-on-pima-diabetes-full-data</loc><lastmod>2026-06-09T07:13:04.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tool-use-on-multi-step-tool-calling-tasks-model-aggregate-test</loc><lastmod>2026-06-09T07:13:04.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intrusion-detection-on-nsl-kdd-accuracy-and-latency</loc><lastmod>2026-06-25T08:00:51.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mmse-score-prediction-on-mmse-m60</loc><lastmod>2026-06-09T07:03:01.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/iov-defense-strategy-on-iov-security-environment-80-episodes-test</loc><lastmod>2026-06-09T07:03:01.479Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/symbolic-regression-on-llm-srbench-129-task-synthetic-subset-ood-test</loc><lastmod>2026-06-09T07:02:59.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/group-affect-recognition-on-gaf-3-0-val</loc><lastmod>2026-06-09T06:52:55.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inference-system-performance-on-live-inference-service-kubernetes-production-environment</loc><lastmod>2026-06-09T06:52:54.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intelligent-autoscaling-on-walmart-microservices-production</loc><lastmod>2026-06-09T06:45:09.192Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intelligent-autoscaling-on-walmart-production-microservices</loc><lastmod>2026-06-09T06:45:09.169Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reinforcement-learning-on-darkroom2-5x5-grid-0-4</loc><lastmod>2026-06-09T06:42:53.274Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cate-estimation-on-10d-multi-dimensional-simulation-target</loc><lastmod>2026-06-09T06:42:52.955Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mnist-c-zigzag</loc><lastmod>2026-06-09T06:42:52.171Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mnist-c-stripe-accuracy</loc><lastmod>2026-06-09T06:42:52.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mnist-c-brightness</loc><lastmod>2026-06-09T06:42:52.087Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/npvh-vs-npvh-control-classification-on-neckvibe-10-fold-cross-validation</loc><lastmod>2026-06-09T06:42:51.386Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pvh-vs-pvh-control-classification-on-neckvibe-10-fold-cross-val</loc><lastmod>2026-06-09T06:42:51.349Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-video-generation-on-vimax-bench-overall</loc><lastmod>2026-06-09T06:42:50.539Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-video-generation-on-vimax-bench-long</loc><lastmod>2026-06-09T06:42:50.498Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-video-generation-on-vimax-bench-medium</loc><lastmod>2026-06-09T06:42:50.452Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-planning-on-narrativeqa-novel-to-video-adaptation-setting</loc><lastmod>2026-06-09T06:42:50.411Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/air-quality-classification-on-traqid-within-city</loc><lastmod>2026-06-09T06:42:50.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-on-realworldqa</loc><lastmod>2026-06-09T06:35:31.741Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-on-mmmu</loc><lastmod>2026-06-09T06:35:31.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-on-mmbench-en-dev</loc><lastmod>2026-06-09T06:35:31.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-on-mmbench-cn-dev</loc><lastmod>2026-06-09T06:35:31.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-word-prediction-on-article-title-benchmark</loc><lastmod>2026-06-09T06:33:00.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-asgdts-full</loc><lastmod>2026-06-09T06:32:47.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/swiss-german-asr-on-cross-corpus-evaluation-set</loc><lastmod>2026-06-09T06:32:47.804Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-threshold-metric</loc><lastmod>2026-06-09T06:22:44.016Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-accuracy-and-threshold-metrics</loc><lastmod>2026-06-09T06:22:43.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-problem-solving-on-math-accuracy-and-throughput</loc><lastmod>2026-06-09T06:22:43.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-retrieval-on-geoplan-bench-complex</loc><lastmod>2026-06-09T06:22:43.117Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-retrieval-on-geoplan-bench-medium</loc><lastmod>2026-06-09T06:22:43.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-retrieval-on-geoplan-bench-simple</loc><lastmod>2026-06-09T06:22:43.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-relation-prediction-on-model-relation-prediction-dataset-135-pairs</loc><lastmod>2026-06-09T06:22:42.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ldct-denoising-on-deeplesion-ldct-simulated-10-percent-dose-noise-test</loc><lastmod>2026-06-09T06:22:42.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-strongreject-llama-3-3-70b</loc><lastmod>2026-06-09T06:22:42.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-strongreject-claude-opus-4-1</loc><lastmod>2026-06-09T06:22:42.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-strongreject-deepseek-r1</loc><lastmod>2026-06-09T06:22:42.116Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-strongreject-openai-o1</loc><lastmod>2026-06-09T06:22:42.080Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-strongreject-openai-o3</loc><lastmod>2026-06-09T06:22:42.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-performance-prediction-on-task-solver-pool-held-out</loc><lastmod>2026-06-09T06:03:49.043Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-loop-planning-on-roadwork4d-cl-cls-r-v1-0-closed-loop</loc><lastmod>2026-06-08T07:58:19.085Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-loop-planning-on-roadwork4d-cl-cls-nr-v1-0-closed-loop</loc><lastmod>2026-06-08T07:58:19.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-detection-on-gcg_adapt-jailbreak-prompts-vicuna-7b-test</loc><lastmod>2026-06-08T07:52:32.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-detection-on-gcg_adapt-jailbreak-prompts-llama2-7b-test</loc><lastmod>2026-06-08T07:52:32.503Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-video-generation-on-ue-static-cinescene-test</loc><lastmod>2026-06-08T07:52:31.906Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/egocentric-video-generation-on-egocentric-static-test</loc><lastmod>2026-06-08T07:52:31.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-class-discovery-on-semantickitti-split-4</loc><lastmod>2026-06-08T07:46:11.017Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-class-discovery-on-semantickitti-split-3</loc><lastmod>2026-06-08T07:46:10.995Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-class-discovery-on-semantickitti-split-2</loc><lastmod>2026-06-08T07:46:10.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-class-discovery-on-semantickitti-split-1</loc><lastmod>2026-06-08T07:46:10.944Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-class-discovery-on-semanticposs-split-3</loc><lastmod>2026-06-08T07:46:10.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/novel-class-discovery-on-semanticposs-split-2</loc><lastmod>2026-06-08T07:46:10.894Z</lastmod></url></urlset>