AI RESEARCH
Component-Aware Self-Speculative Decoding in Hybrid Language Models
arXiv CS.CL
•
ArXi:2605.01106v1 Announce Type: new Speculative decoding accelerates autoregressive inference by drafting candidate tokens with a fast model and verifying them in parallel with the target. Self-speculative methods avoid the need for an external drafter but have been studied exclusively in homogeneous Transformer architectures. We