A segment-wise flow matching model learns continuous dynamics of beam power vectors conditioned on vision data to improve accuracy and slash inference latency in mmWave vehicle-to-infrastructure beam prediction.
Flow straight and fast: Lear ning to generate and transfer data with rectified flow,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Segment-Wise Flow Matching for Vision-Aided mmWave V2I Beam Prediction
A segment-wise flow matching model learns continuous dynamics of beam power vectors conditioned on vision data to improve accuracy and slash inference latency in mmWave vehicle-to-infrastructure beam prediction.