Shi, L., Li, Z., Zhang, L., Qi, B., Liu, G., & Zhao, H. (2026). Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios. Proceedings of the AAAI Conference on Artificial Intelligence, 40(39), 32947–32955. https://doi.org/10.1609/aaai.v40i39.40576