https://arxiv.org/abs/2602.06036 - they use a faster (single-pass) diffusion model to generate predictions for 7 to 15 tokens in a single step. Then if they're accepted that really speeds up the autoregressive model because it doesn't have to generate tokens one at a time.

I'm pretty sure fast speculative decoding models need to have the same objective (NTP, MDM, NCM) as the larger model they try to accelerate.

Just for additional context: You have to do more computational work to check them, beyond the extra work in the drafter, but you have much less of a memory bottleneck, which is extremely worth it on current hardware.