BayesianPseudoPosteriorMechanismforDifferentiallyPrivateMachineLearning
Differential privacy (DP) is becoming increasingly important for deployed machine learning applicati
首頁 > 研究論文
-
-
Constraint-basedcausaldiscoverywithtieredbackgroundknowledgeandlatentvariablesinsingleoroverlappingdatasets
In this paper we consider the use of tiered background knowledge within constraint based causal disc
-
Uncertainty-awareBayesianmachinelearningmodellingoflandcoverclassification
Land cover classification involves the production of land cover maps, which determine the type of la
-
F-INR:FunctionalTensorDecompositionforImplicitNeuralRepresentations
Implicit Neural Representation (INR) has emerged as a powerful tool for encoding discrete signals in
-
RobustDNNPartitioningandResourceAllocationUnderUncertainInferenceTime
In edge intelligence systems, deep neural network (DNN) partitioning and data offloading can provide
-
DeepRV:pre-trainedspatialpriorsforaccelerateddiseasemapping
Recently introduced prior-encoding deep generative models (e.g., PriorVAE, $\pi$VAE, and PriorCVAE)
-
EnhancingUnderwaterNavigationthroughCross-Correlation-AwareDeepINS/DVLFusion
The accurate navigation of autonomous underwater vehicles critically depends on the precision of Dop
-
LetHumanoidsHike!IntegrativeSkillDevelopmentonComplexTrails
Hiking on complex trails demands balance, agility, and adaptive decision-making over unpredictable t
-
Neuro-SymbolicConcepts
This article presents a concept-centric paradigm for building agents that can learn continually and
-
Query-drivenDocument-levelScientificEvidenceExtractionfromBiomedicalStudies
Extracting scientific evidence from biomedical studies for clinical research questions (e.g., Does s
-
Turbo-ICL:In-ContextLearning-BasedTurboEqualization
This paper introduces a novel in-context learning (ICL) framework, inspired by large language models
-
MM-Skin:EnhancingDermatologyVision-LanguageModelwithanImage-TextDatasetDerivedfromTextbooks
Medical vision-language models (VLMs) have shown promise as clinical assistants across various medic
-
AScalingLawforTokenEfficiencyinLLMFine-TuningUnderFixedComputeBudgets
We introduce a scaling law for fine-tuning large language models (LLMs) under fixed compute budgets
-
EfficientSensorimotorLearningforOpen-worldRobotManipulation
This dissertation considers Open-world Robot Manipulation, a manipulation problem where a robot must
-
WassersteinDistancesMadeExplainable:InsightsintoDatasetShiftsandTransportPhenomena
Wasserstein distances provide a powerful framework for comparing data distributions. They can be use
-
TheApplicationofDeepLearningforLymphNodeSegmentation:ASystematicReview
Automatic lymph node segmentation is the cornerstone for advances in computer vision tasks for early
-
UniVLA:LearningtoActAnywherewithTask-centricLatentActions
A generalist robot should perform effectively across various environments. However, most existing ap
-
MultimodalSentimentAnalysisonCMU-MOSEIDatasetusingTransformer-basedModels
This project performs multimodal sentiment analysis using the CMU-MOSEI dataset, using transformer-b
-
LLMsOutperformExpertsonChallengingBiologyBenchmarks
This study systematically evaluates 27 frontier Large Language Models on eight diverse biology bench
-
FreeandFairHardware:APathwaytoCopyrightInfringement-FreeVerilogGenerationusingLLMs
Limitations in Large Language Model (LLM) capabilities for hardware design tasks, such as generating
