About this paper
A lightweight feature-encoding method with rejection memory and architectural enhancements enables faster large language model inference by improving speculative-diffusion draft verification.
Speculative-diffusion decoding uses a small parallel drafter model to generate b draft tokens in one forward pass, which then undergo parallel verification via a larger target model. Faster inference can be achieved when multiple draft tokens pass verification simultaneously. Recent parallel draft architectures (DFlash, DSpark) improve draft quality by conditioning on rich features computed by the target, through a mechanism known as feature encoding. However, standard feature encoding mechanisms have three limitations: (1) they are lossy, applying encoding projections that are destructive to the underlying target feature-space via a discovered effect known as residual mixing, (2) they are…
speculative-diffusion decodingparallel drafter modeldraft tokenstarget modelparallel verificationparallel draft architecturesDFlashDSparkfeature encodingresidual mixing
- Upvotes
- 4
- Authors
- 8
- Published
- Nov 16, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 7 checks on 1 different day. Its best position was #18 of 30, reached on Nov 19, 11:29 UTC. It dropped off the list after Nov 19, 13:29 UTC.