Wang, Z., Müller, K., Filipovich, M., Launay, J., Ohana, R., Pariente, G., Mokaadi, S., Brossollet, C., Moreau, F., Cappelli, A., Poli, I., Carron, I., Daudet, L., Krzakala, F., Gigan, S. (2026). Streamlined optical training of large-scale modern deep learning architectures with direct feedback alignment. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2532022123