TowardsPrincipledMulti-AgentTaskAgnosticExploration
In reinforcement learning, we typically refer to task-agnostic exploration when we aim to explore th
首页 > 研究论文
-
-
ASurveyonPre-TrainedDiffusionModelDistillations
Diffusion Models~(DMs) have emerged as the dominant approach in Generative Artificial Intelligence (
-
Top-ThetaAttention:SparsifyingTransformersbyCompensatedThresholding
The attention mechanism is essential for the impressive capabilities of transformer-based Large Lang
-
TrustworthyGNNswithLLMs:ASystematicReviewandTaxonomy
With the extensive application of Graph Neural Networks (GNNs) across various domains, their trustwo
-
GraphFoundationModelsforRecommendation:AComprehensiveSurvey
Recommender systems (RS) serve as a fundamental tool for navigating the vast expanse of online infor
-
HierarchicalLearning-basedGraphPartitionforLarge-scaleVehicleRoutingProblems
Neural solvers based on the divide-and-conquer approach for Vehicle Routing Problems (VRPs) in gener
-
HierarchicalMulti-AgentFrameworkforCarbon-EfficientLiquid-CooledDataCenterClusters
Reducing the environmental impact of cloud computing requires efficient workload distribution across
-
Salience-InvariantConsistentPolicyLearningforGeneralizationinVisualReinforcementLearning
Generalizing policies to unseen scenarios remains a critical challenge in visual reinforcement learn
-
ModificationandGenerated-TextDetection:AchievingDualDetectionCapabilitiesfortheOutputsofLLMbyWatermark
The development of large language models (LLMs) has raised concerns about potential misuse. One prac
-
MitigatingHallucinationsinMultimodalSpatialRelationsthroughConstraint-AwarePrompting
Spatial relation hallucinations pose a persistent challenge in large vision-language models (LVLMs),
-
HDT:HierarchicalDiscreteTransformerforMultivariateTimeSeriesForecasting
Generative models have gained significant attention in multivariate time series forecasting (MTS), p
-
CompromisingHonestyandHarmlessnessinLanguageModelsviaDeceptionAttacks
Recent research on large language models (LLMs) has demonstrated their ability to understand and emp
-
ImprovingExistingOptimizationAlgorithmswithLLMs
The integration of Large Language Models (LLMs) into optimization has created a powerful synergy, op
-
CRISP:AFrameworkforCryo-EMImageSegmentationandProcessingwithConditionalRandomField
Differentiating signals from the background in micrographs is a critical initial step for cryogenic
-
SportsBuddy:DesigningandEvaluatinganAI-PoweredSportsVideoStorytellingToolThroughReal-WorldDeployment
Video storytelling is essential for sports performance analysis and fan engagement, enabling sports
-
ScalableThermodynamicSecond-orderOptimization
Many hardware proposals have aimed to accelerate inference in AI workloads. Less attention has been
-
SPeCtrum:AGroundedFrameworkforMultidimensionalIdentityRepresentationinLLM-BasedAgent
Existing methods for simulating individual identities often oversimplify human complexity, which may
-
IssueBench:MillionsofRealisticPromptsforMeasuringIssueBiasinLLMWritingAssistance
Large language models (LLMs) are helping millions of users write texts about diverse issues, and in
-
AdvSwap:CovertAdversarialPerturbationwithHighFrequencyInfo-swappingforAutonomousDrivingPerception
Perception module of Autonomous vehicles (AVs) are increasingly susceptible to be attacked, which ex
-
FoundationModelsinComputationalPathology:AReviewofChallenges,Opportunities,andImpact
From self-supervised, vision-only models to contrastive visual-language frameworks, computational pa
热门文章
