SyncAI.news, a Varaisys broadcasting
DynaDFlash: Dynamic Feature Projection for Block Diffusion Speculators
AK

Aadi Kulshrestha, Reese Chong

· 1 min read

ResearcharXiv cs.LG

DynaDFlash: Dynamic Feature Projection for Block Diffusion Speculators

arXiv:2611.19085v1 Announce Type: new Abstract: DFlash trains a parallel draft model on hidden features from its target model. Inspired by the previous work of DFlare that introduced per layer combinations of target hidden states, we test whether context dependent weighting of these states helps improve acceptance length of block diffusion speculators. We trained both a DFlash baseline for the Qwen 3 of block size 16, and a dynamic model that computes gates for each layer to affect the magnitude of hidden features before projection. While mean acceptance length between the dynamic model and the DFlash baseline didn't significantly differ, we notice that the dynamic model excels for drafting in the context of math. In an evaluation of 700 prompts from the MetaMathQA and Orca-Math datasets, the mean accepted length improves by 5%. We also found this lead to a 4.1% higher throughput for a subset of the same dataset in the context of speculative decoding.

Original source

This story was published by arXiv cs.LG and written by Aadi Kulshrestha, Reese Chong. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News