Pith. sign in

REVIEW 16 cited by

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models

Not yet reviewed by Pith; the record is open.

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 2406.01572 v4 pith:QJ27HOLP submitted 2024-06-03 cs.LG

classification cs.LG
keywords discreteguidancemodelsstate-spacesapplicationsdesireddiffusionflow
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has been realized using guidance on diffusion and flow models. However, these guidance approaches are not readily amenable to discrete state-space models. Consequently, we introduce a general and principled method for applying guidance on such models. Our method depends on leveraging continuous-time Markov processes on discrete state-spaces, which unlocks computational tractability for sampling from a desired guided distribution. We demonstrate the utility of our approach, Discrete Guidance, on a range of applications including guided generation of small-molecules, DNA sequences and protein sequences.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

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

  1. Language Modeling with Hyperspherical Flows

    cs.LG 2026-05 unverdicted novelty 8.0 of 10

    S-FLM rotates vectors on a hypersphere using a learned velocity field to generate language sequences, improving continuous flow models on large-vocabulary reasoning and closing the gap to masked diffusion at standard ...

  2. Adaptive Order Policies for Masked Diffusion

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.

  3. Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    CDM amortizes SMC inference for reward-tilted discrete diffusion by training a parameterized twist function on contrastive samples with closed-form kernels.

  4. Language Modeling with Hyperspherical Flows

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    S-FLM is a hyperspherical latent flow language model that improves continuous flow language models on large-vocabulary reasoning tasks and closes the gap to masked diffusion at standard sampling temperature.

  5. Binomial flows: Denoising and flow matching for discrete ordinal data

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Binomial flows close the gap between continuous flow matching and discrete ordinal data by using binomial distributions to enable unified denoising, sampling, and exact likelihoods in diffusion models.

  6. GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning

    cs.LG 2026-03 conditional novelty 6.5 of 10

    GeMPO unifies diffusion RL reweighting as measure matching to a regularized target, enabling flexible and negative weights that improve exploration and performance.

  7. Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes

    cs.LG 2026-07 conditional novelty 6.0 of 10

    CO2Jump couples text and image denoising through cross-modal attention and remasking, achieving best joint accuracy on three concurrent-generation tasks.

  8. Flexible Flows for Biological Sequence Design

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Enhances Discrete Flow Matching with domain-specific couplings, latent edit-based rates, latent classifier-free guidance, and temperature scaling to reach SOTA on DNA and peptide sequence tasks.

  9. BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    BlockGen enables flexible blockwise diffusion modeling with mixed block sizes and ARPC sampling, finding uniform diffusion outperforms masked under ancestral sampling in few-step regimes while the gap reverses with AR...

  10. Language Modeling with Hyperspherical Flows

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    S-FLM is a hyperspherical latent flow language model that learns velocity fields on the unit sphere to generate token sequences via deterministic ODE integration without materializing one-hot vectors.

  11. Interpolating Discrete Diffusion Models with Controllable Resampling

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    IDDM interpolates diffusion transitions with a resampling mechanism to lessen dependence on intermediate latents and improve sample quality over masked and uniform discrete diffusion models.

  12. Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space

    stat.ML 2025-10 unverdicted novelty 6.0 of 10

    Proposes Latent Interacting Particle Systems with an efficient parameterization of twist potentials to enable approximate posterior inference for coupled continuous-time hidden Markov models via twisted sequential Mon...

  13. Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces

    cs.LG 2025-09 unverdicted novelty 6.0 of 10

    A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent ...

  14. On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization

    cs.LG 2026-07 conditional novelty 5.5 of 10

    Online fine-tuning of discrete diffusion models with complementary acquisition, CVaR shaping, density-entropy debiasing, replay, and validity control finds better molecules under fixed oracle budgets than offline fine...

  15. Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance

    cs.CV 2025-09 conditional novelty 5.0 of 10

    IGG, an attention-based reweighting of classifier-free guidance, concentrates guidance on important tokens and modestly improves FID/IS in scale-wise autoregressive image generation.

  16. A Mathematical Introduction to Diffusion Models

    cs.LG 2026-07 unverdicted

    An educational exposition that layers core definitions, simplified estimates, and research-level theorems on diffusion sampling for probability-background graduate students.

Pith tools