Pith. sign in

REVIEW 7 cited by

Diffusion Models for Constrained Domains

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 2304.05364 v2 pith:YCA4X775 submitted 2023-04-11 cs.LG stat.ML

Diffusion Models for Constrained Domains

classification cs.LG stat.ML
keywords diffusionmodelstasksappliedconstraintsdomainsframeworkincluding
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-image tasks. Building on this success, diffusion models have recently been extended to the Riemannian manifold setting, broadening their applicability to a range of problems from the natural and engineering sciences. However, these Riemannian diffusion models are built on the assumption that their forward and backward processes are well-defined for all times, preventing them from being applied to an important set of tasks that consider manifolds defined via a set of inequality constraints. In this work, we introduce a principled framework to bridge this gap. We present two distinct noising processes based on (i) the logarithmic barrier metric and (ii) the reflected Brownian motion induced by the constraints. As existing diffusion model techniques cannot be applied in this setting, we derive new tools to define such models in our framework. We then demonstrate the practical utility of our methods on a number of synthetic and real-world tasks, including applications from robotics and protein design.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

    cs.CL 2026-05 unverdicted novelty 8.0

    REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reason...

  2. DiPhon: Diffusion on Graphons for Scalable Graph Generation

    stat.ML 2026-07 conditional novelty 7.0

    A Jacobi diffusion on graphon space is discretized into a graph-level generative process that matches the continuous process's first moment exactly and second moment up to a closed-form gap, enabling out-of-scale grap...

  3. Motion Planning with Model-Based Diffusion via Constraint Optimization and Adaptive Scheduling

    cs.RO 2026-07 conditional novelty 6.0

    MD-COAS unifies inexact augmented-Lagrangian soft constraints with convex-feasible-set hard projection and adaptively schedules them during model-based diffusion, improving safe and successful planning in non-convex e...

  4. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

    cs.CL 2026-05 unverdicted novelty 6.0

    REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-sou...

  5. Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling

    cs.CV 2026-02 unverdicted novelty 6.0

    Picasso produces multi-object scene reconstructions that are both geometrically accurate and physically plausible by using physics-constrained rejection sampling over an inferred contact graph, outperforming prior met...

  6. Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling

    cs.CV 2026-02 conditional novelty 6.0

    Picasso is an inference-time pose corrector that uses physics-constrained rejection sampling and a contact scene graph to make multi-object scene reconstructions physically plausible and often more accurate.

  7. Bayesian Inference of Discretization Error Means in ODEs via Ensemble Kalman Filtering

    math.NA 2026-07 conditional novelty 4.0

    A Bayesian state-space model with an Ensemble Kalman Filter infers the mean of ODE discretization errors from noisy observations, using a step-size-dependent Markov prior whose convergence is proven.