Speculative decoding accelerates autoregressive inference by verifying multiple draft tokens in a single target forward pass. However, as the context grows, existing state-of-the-art drafters become increasingly expensive, eroding the very efficiency advantage they are designed to provide. We argue that this scaling is...
The studied model realizes only part of the flexibility afforded by four-stream mHC: individual blocks rarely require all four streams, and late residual mixing provides little measured benefit.
Peng-Xiang Zhao, Xing Li, Xian-Zhi Yu et al.· 1 citation
AdaFlash framework is proposed, comprising two components: an on-policy distillation algorithm with reverse-KL divergence tailored for diffusion drafters, bringing stable convergence and effectively reducing domain-level variance and an adaptive length head that dynamically adjusts the candidate sequence length on the...