Pith. sign in

REVIEW 4 cited by

Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo

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 2502.06079 v3 pith:NPHUYEC7 submitted 2025-02-10 cs.LG

Cheuk Kit Lee , Paul Jeha , Jes Frellsen , Pietro Lio , Michael Samuel Albergo , Francisco Vargas This is my paper · ORCID
classification cs.LG
keywords distributiondiscretecarlodatadiffusionguidancemodelsmonte
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Discrete diffusion models are a class of generative models that produce samples from an approximated data distribution within a discrete state space. Often, there is a need to target specific regions of the data distribution. Current guidance methods aim to sample from a distribution with mass proportional to $p_0(x_0) p(\zeta|x_0)^\alpha$ but fail to achieve this in practice. We introduce a Sequential Monte Carlo algorithm that generates unbiasedly from this target distribution, utilising the learnt unconditional and guided process. We validate our approach on low-dimensional distributions, controlled images and text generations. For text generation, our method provides strong control while maintaining low perplexity compared to guidance-based approaches.

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. Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Bootstrap Flow-Map Trees construct complete DDPM-like trajectories with a single NFE and dynamic steps, enabling efficient online feedback-driven search and alignment that beats prior tree and SMC samplers.

  2. Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance

    cs.LG 2025-05 conditional novelty 7.0 of 10

    CFG is missing a Rényi divergence repulsion term, and the new CFG IG sampler uses iterative noising and denoising to preserve diversity while improving conditional generation quality.

  3. Provable Diffusion Posterior Sampling for Bayesian Inversion

    stat.ML 2025-12 conditional novelty 6.0 of 10

    A diffusion posterior sampler using Monte Carlo Langevin score estimation and warm start is proven to converge in Wasserstein-2 distance under semi-log-concavity and sub-Gaussian assumptions, and outperforms DPS/TV on...

  4. Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.

Pith tools