A heterogeneous mixture-of-experts RL architecture optimizes energy-efficient multimodal ISAC in mobile V2I networks by achieving event-triggered sensing policies that minimize long-term costs while ensuring low sensing errors and reliable links.
The roadmap to 6g: Ai empowered wireless networks,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
AutoFLIP prunes federated models via one-time collective loss-landscape mapping and client-agreement-guided adaptation, reporting 52% lower computation and 65% lower communication with SOTA non-IID accuracy.
citing papers explorer
-
Heterogeneous Mixture-of-Experts for Energy-Efficient Multimodal ISAC in Highly Mobile Networks
A heterogeneous mixture-of-experts RL architecture optimizes energy-efficient multimodal ISAC in mobile V2I networks by achieving event-triggered sensing policies that minimize long-term costs while ensuring low sensing errors and reliable links.
-
Pruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring
AutoFLIP prunes federated models via one-time collective loss-landscape mapping and client-agreement-guided adaptation, reporting 52% lower computation and 65% lower communication with SOTA non-IID accuracy.