Pith. sign in

REVIEW 4 cited by

Accelerated Diffusion Models via Speculative Sampling

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.05370 v2 pith:YRBYYX2J submitted 2025-01-09 cs.LG stat.ML

Valentin De Bortoli , Alexandre Galashov , Arthur Gretton , Arnaud Doucet This is my paper · ORCID
classification cs.LGstat.ML
keywords modeldiffusionmodelssamplingspeculativetargetdraftgenerating
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Speculative sampling is a popular technique for accelerating inference in Large Language Models by generating candidate tokens using a fast draft model and accepting or rejecting them based on the target model's distribution. While speculative sampling was previously limited to discrete sequences, we extend it to diffusion models, which generate samples via continuous, vector-valued Markov chains. In this context, the target model is a high-quality but computationally expensive diffusion model. We propose various drafting strategies, including a simple and effective approach that does not require training a draft model and is applicable out of the box to any diffusion model. Our experiments demonstrate significant generation speedup on various diffusion models, halving the number of function evaluations, while generating exact samples from the target model.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CachedSearch: Training-Free Cached Exploration for Test-Time Search in Video Diffusion

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Using cached drafts to select the winner and regenerating only that winner captures 94.7% of best-of-8 search gain at 63% of the cost.

  2. Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Spiffy speeds up diffusion LLM inference up to about 3x (and up to 7.9x with parallel decoding) by verifying multiple candidate unmasked states in one batched model call, while preserving greedy output.

  3. Playing with Transformer at 30+ FPS via Next-Frame Diffusion

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Next-Frame Diffusion combines block-wise causal attention, consistency distillation, and action-based speculative sampling to generate action-conditioned Minecraft video at over 30 FPS on an A100 with a 310M parameter model.

  4. Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking

    cs.LG 2025-05 conditional novelty 6.0 of 10

    EB-Sampler dynamically unmasks multiple low-entropy tokens per function evaluation, accelerating masked diffusion model sampling by 2-3x with negligible accuracy loss.

Pith tools