Attention Is All You Need, Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, 2017Advances in Neural Information Processing Systems (NeurIPS 2017)DOI: 10.48550/arXiv.1706.03762 - The seminal paper that introduced the Transformer model, which is a core component providing the global context modeling capability of the Conformer architecture.
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam, 2017arXiv preprint arXiv:1704.04861DOI: 10.48550/arXiv.1704.04861 - Introduces and details depthwise separable convolutions, a highly efficient form of convolution used within the Conformer's convolution module for local pattern detection.