We propose the first tensorized optical multimodal fusion network architecture with a self-attention mechanism and low-rank tensor fusion. Simulation results show $51.3 \times$ less hardware requirement and $3.7\times 10^{13}$ MAC/J energy efficiency.

翻译：我们提出了首个具有自注意力机制和低秩张量融合的张量化光学多模态融合网络架构。仿真结果表明，硬件需求降低至原来的$51.3 \times$分之一，能效达到$3.7\times 10^{13}$ MAC/J。