PR-HBFNet combines a Transformer encoder for per-element pattern selection with model-driven residual learning for analog-digital precoding in RPA-equipped HAPS MIMO, approaching greedy spectral efficiency at lower complexity.
A Vision and Framework for the High Altitude Platform Station (HAPS) Networks of the Future,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Transformer-Based Hybrid Beamforming with Reconfigurable Pixel Antenna for HAPS Communications
PR-HBFNet combines a Transformer encoder for per-element pattern selection with model-driven residual learning for analog-digital precoding in RPA-equipped HAPS MIMO, approaching greedy spectral efficiency at lower complexity.