SMM Transformer uses spiking neurons, spike-driven token mixing, and a spiking mixture of experts to reach ANN-comparable accuracy on vision and vision-language tasks with lower estimated compute energy.
Proceedings of the seventh IEEE international conference on computer vision , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SMM Transformer: Leveraging Spiking Neural Networks for Multimodal Tasks
SMM Transformer uses spiking neurons, spike-driven token mixing, and a spiking mixture of experts to reach ANN-comparable accuracy on vision and vision-language tasks with lower estimated compute energy.