Gao, Z., Xia, Q., Xu, T., Duan, X., Zheng, Z., Wang, Z. and Chen, E. 2025. Multi-Branch Self-Drafting for LLM Inference Acceleration. Proceedings of the AAAI Conference on Artificial Intelligence. 39, 22 (Apr. 2025), 23942-23950. DOI:https://doi.org/10.1609/aaai.v39i22.34567.