CAT-MoEformer achieves 94.88% top-1 and 80.62% beam switching accuracy on 3GPP Urban Macro simulations using scene-conditioned MoE in a GPT-2 backbone, with gains over a CNN+GPT-2 baseline.
Leiet al., ”LLM-MM: End-to-end robust multimodal beam prediction for 6G V2X networks via MoE-LoRA adaptation,”IEEE Journal on Selected Areas in Communications, vol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CAT-MoEformer: Context-Aware Temporal MoE Transformer for Beam Prediction
CAT-MoEformer achieves 94.88% top-1 and 80.62% beam switching accuracy on 3GPP Urban Macro simulations using scene-conditioned MoE in a GPT-2 backbone, with gains over a CNN+GPT-2 baseline.