Trendoday

LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers

Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers. During autoregressive decoding, however, generating each token requires several sequential passes t

  • Upvotes4
–Rank now
#26Peak rank
2Days on list
29Score · 7d
Nov 17, 2026First seen
Rank · 7 days

About this paper

LoopFill reduces decoding latency for looped language models by combining multi-token suffix drafts and shallow-loop predictions into a single draft tree with full-depth verification that preserves the autoregressive output distribution.

Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers. During autoregressive decoding, however, generating each token requires several sequential passes through these layers, leading to high decoding latency. Pipelined self-speculative methods use shallow-loop predictions to process tokens at different loops in the same batch, but each token must reach the drafting depth before the next can enter the pipeline. We introduce LoopFill, a training-free speculative decoding algorithm for looped LLM that combines multi-token suffix drafts with shallow-loop predictions in a single draft tree. Both drafters contribute to one tree, so a suffix lookup…

Looped Transformersparameter efficiencyTransformer layersautoregressive decodingdecoding latencypipelined self-speculative methodsshallow-loop predictionsspeculative decodinglooped LLMmulti-token suffix drafts
Upvotes
4
Authors
4
Published
Nov 14, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 4 checks on 2 different days. Its best position was #26 of 30, reached on Nov 17, 21:28 UTC. It dropped off the list after Nov 18, 01:28 UTC.

Rank history

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

#1#11#20#30 19:2820:5822:2823:5801:28 Nov 17, 19:28 UTC · #29Nov 17, 21:28 UTC · #26Nov 17, 23:28 UTC · #27Nov 18, 01:28 UTC · #26

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0134 19:2820:5822:2823:5801:28 Nov 17, 19:28 UTC · 4Nov 17, 21:28 UTC · 4Nov 17, 23:28 UTC · 4Nov 18, 01:28 UTC · 4

Questions

Is LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 18, 01:28 UTC, after 2 days of trending.

What is the highest rank LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers reached?

#26 on Hugging Face · Daily papers, on Nov 17, 21:28 UTC. Trendoday checks this list every 120 minutes.

How long has LoopFill: Pipelined Multi-Token Speculative Decoding for Looped Transformers been trending?

It was first seen on Nov 17, 2026 and has been on the list on 2 days (4 checks) since.