Embodied-Reasoner:SynergizingVisualSearch,Reasoning,andActionforEmbodiedInteractiveTasks
Recent advances in deep thinking models have demonstrated remarkable reasoning capabilities on mathe
首页 > 研究论文
-
-
ADeepReinforcementLearning-basedApproachforAdaptiveHandoverProtocols
The use of higher frequencies in mobile communication systems leads to smaller cell sizes, resulting
-
Bearingfaultdiagnosisbasedonmulti-scalespectralimagesandconvolutionalneuralnetwork
To address the challenges of low diagnostic accuracy in traditional bearing fault diagnosis methods,
-
ShapeModelingofLongitudinalMedicalImages:FromDiffeomorphicMetricMappingtoDeepLearning
Living biological tissue is a complex system, constantly growing and changing in response to externa
-
Dual-TaskLearningforDeadTreeDetectionandSegmentationwithHybridSelf-AttentionU-NetsinAerialImagery
Mapping standing dead trees is critical for assessing forest health, monitoring biodiversity, and mi
-
StochasticEngramsforEfficientContinualLearningwithBinarizedNeuralNetworks
The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrop
-
BrainAgeGroupClassificationBasedonRestingStateFunctionalConnectivityMetrics
This study investigated age-related changes in functional connectivity using resting-state fMRI and
-
ProHOC:ProbabilisticHierarchicalOut-of-DistributionClassificationviaMulti-DepthNetworks
Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task,
-
LandMarkSystemTechnicalReport
3D reconstruction is vital for applications in autonomous driving, virtual reality, augmented realit
-
InvestigatingtheDualityofInterpretabilityandExplainabilityinMachineLearning
The rapid evolution of machine learning (ML) has led to the widespread adoption of complex "black bo
-
AData-DrivenMethodforINS/DVLAlignment
Autonomous underwater vehicles (AUVs) are sophisticated robotic platforms crucial for a wide range o
-
ResidualLearningInspiredCrossoverOperatorandStrategyEnhancementsforEvolutionaryMultitasking
In evolutionary multitasking, strategies such as crossover operators and skill factor assignment are
-
ExplainableBoostingMachineforPredictingClaimSeverityandFrequencyinCarInsurance
In a context of constant increase in competition and heightened regulatory pressure, accuracy, actua
-
DeBackdoor:ADeductiveFrameworkforDetectingBackdoorAttacksonDeepModelswithLimitedData
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In
-
Simulation-informeddeeplearningforenhancedSWOTobservationsoffine-scaleoceandynamics
Oceanic processes at fine scales are crucial yet difficult to observe accurately due to limitations
-
DelvingDeepintoSemanticRelationDistillation
Knowledge distillation has become a cornerstone technique in deep learning, facilitating the transfe
-
OrangeQualityGradingwithDeepLearning
Orange grading is a crucial step in the fruit industry, as it helps to sort oranges according to dif
-
ExploringtheRastallGravityCosmologicalModelusingGong-ZhangparameterizationwithLatestObservationalDataandDeepLearningTechniques
In this study, we have explored the cosmological dynamics of an isotropic, homogeneous universe in R
-
Feature-EnhancedMachineLearningforAll-CauseMortalityPredictioninHealthcareData
Accurate patient mortality prediction enables effective risk stratification, leading to personalized
-
InterpretableCross-SphereMultiscaleDeepLearningPredictsENSOSkilfullyBeyond2Years
El Niño-Southern Oscillation (ENSO) exerts global climate and societal impacts, but real-time predic
