Pan, Y., Xi, H., Zhu, K., Li, X., Wu, Y., Mishra, M., Zhang, H., Zheng, W. X., Kasikci, B., Han, S., Keutzer, K., Iyer, R., & Stoica, I. (2026). LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization. https://omanscience.com/ar/articles/leapquant-efficient-linear-attention-with-accurate-recurrent-state-quantization