Trendoday

DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding

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

  • Upvotes4
–Rank now
#18Peak rank
1Days on list
84Score · 7d
Nov 19, 2026First seen
Rank · 7 days

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.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 01:2804:2807:2910:2913:29 Nov 19, 01:28 UTC · #26Nov 19, 03:28 UTC · #29Nov 19, 05:28 UTC · #24Nov 19, 07:29 UTC · #21Nov 19, 09:29 UTC · #20Nov 19, 11:29 UTC · #18Nov 19, 13:29 UTC · #18

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0246 01:2804:2807:2910:2913:29 Nov 19, 01:28 UTC · 4Nov 19, 03:28 UTC · 4Nov 19, 05:28 UTC · 4Nov 19, 07:29 UTC · 4Nov 19, 09:29 UTC · 4Nov 19, 11:29 UTC · 6Nov 19, 13:29 UTC · 6

Questions

Is DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 19, 13:29 UTC, after 1 day of trending.

What is the highest rank DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding reached?

#18 on Hugging Face · Daily papers, on Nov 19, 11:29 UTC. Trendoday checks this list every 120 minutes.

How long has DNeo: Your Parallel Draft Model Needs Better Target Feature Encoding been trending?

It was first seen on Nov 19, 2026 and has been on the list on 1 day (7 checks) since.