Paper Detail

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

Ligong Han, Hao Wang, Han Gao, Kai Xu, Akash Srivastava

huggingface Score 6.8

Published 2026-03-26 · First seen 2026-03-27

General AI

Abstract

Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoising. However, in the few-step regime needed for practical acceleration, standard confidence-thresholded decoding is often brittle: aggressive thresholds hurt quality, while conservative thresholds require unnecessary denoising steps. Existing approaches that address this issue either require additional training or incur extra test-time compute. We present S2D2, a training-free self-speculative decoding framework for block-diffusion language models. Our key observation is that a block-diffusion model becomes autoregressive when the block size is reduced to one, allowing the same pretrained model to act as both drafter and verifier. S2D2 inserts a speculative verification step into standard block-diffusion decoding and uses lightweight routing policies to decide when verification is worth its cost. This yields a hybrid decoding trajectory in which diffusion proposes tokens in parallel, while the autoregressive mode acts as a local sequence-level critic. Across three mainstream block-diffusion families, S2D2 consistently improves the accuracy-speed tradeoff over strong confidence-thresholding baselines. On SDAR, we observe up to 4.7times speedup over autoregressive decoding, and up to 1.57times over a tuned dynamic decoding baseline while improving accuracy by up to 4.5 points. On LLaDA2.1-Mini, S2D2 remains complementary to built-in self-correction, including a conservative setting where it is 4.4times faster than the static baseline with slightly higher accuracy.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{han2026s2d2,
  title = {S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation},
  author = {Ligong Han and Hao Wang and Han Gao and Kai Xu and Akash Srivastava},
  year = {2026},
  abstract = {Block-diffusion language models offer a promising path toward faster-than-autoregressive generation by combining block-wise autoregressive decoding with within-block parallel denoising. However, in the few-step regime needed for practical acceleration, standard confidence-thresholded decoding is often brittle: aggressive thresholds hurt quality, while conservative thresholds require unnecessary denoising steps. Existing approaches that address this issue either require additional training or inc},
  url = {https://huggingface.co/papers/2603.25702},
  keywords = {block-diffusion language models, autoregressive decoding, parallel denoising, confidence-thresholded decoding, speculative decoding, drafter, verifier, lightweight routing policies, hybrid decoding trajectory, self-correction, code available, huggingface daily},
  eprint = {2603.25702},
  archiveprefix = {arXiv},
}

Metadata

{}