ARCHES dynamically switches between AI-based and conventional experts in RAN PHY pipelines at sub-millisecond granularity, delivering 5-7% throughput gains and power savings on uplink channel estimation under varying conditions.
AI/ML for beam management in 5G-advanced: A standardization perspective,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ARCHES: Adaptive Real-Time Switching of AI Models for the RAN
ARCHES dynamically switches between AI-based and conventional experts in RAN PHY pipelines at sub-millisecond granularity, delivering 5-7% throughput gains and power savings on uplink channel estimation under varying conditions.