A five-layer MLOps architecture is proposed as a blueprint for collective learning in connected automated driving systems to support continual safety and performance assurance.
Toward transportation digital twin systems for traffic safety and mobility: A review,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A heterogeneous-agent RL algorithm (SU-HATD3) is proposed to jointly optimize diffusion-model inference offloading, inference parameters, and UAV trajectories in order to maximize a fidelity-delay utility for GAI-empowered intelligent transportation digital twins.
citing papers explorer
-
A Five-Layer MLOps Architecture for Connected Automated Driving
A five-layer MLOps architecture is proposed as a blueprint for collective learning in connected automated driving systems to support continual safety and performance assurance.
-
Joint Task Offloading, Inference Optimization and UAV Trajectory Planning for Generative AI Empowered Intelligent Transportation Digital Twin
A heterogeneous-agent RL algorithm (SU-HATD3) is proposed to jointly optimize diffusion-model inference offloading, inference parameters, and UAV trajectories in order to maximize a fidelity-delay utility for GAI-empowered intelligent transportation digital twins.