Pith. sign in

REVIEW 3 cited by

Non Gaussian Denoising Diffusion Models

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 2106.07582 v1 pith:IF7DZXZL submitted 2021-06-14 cs.LG cs.CVcs.SDeess.AS

Eliya Nachmani , Robin San Roman , Lior Wolf This is my paper · ORCID
classification cs.LGcs.CVcs.SDeess.AS
keywords diffusionnoiseprocessdistributiongaussiangammagenerationgenerative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion process is Gaussian noise. However, fitting distributions with more degrees of freedom, could help the performance of such generative models. In this work, we investigate other types of noise distribution for the diffusion process. Specifically, we show that noise from Gamma distribution provides improved results for image and speech generation. Moreover, we show that using a mixture of Gaussian noise variables in the diffusion process improves the performance over a diffusion process that is based on a single distribution. Our approach preserves the ability to efficiently sample state in the training diffusion process while using Gamma noise and a mixture of noise.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. HyperNet-Adaptation for Diffusion-Based Test Case Generation

    cs.LG 2026-01 accept novelty 7.0 of 10

    HyNeA adapts a diffusion model's hypernetwork per test case to generate realistic, failure-inducing inputs for deep learning systems without curated failure data.

  2. Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A diffusion model's training loss and output quality depend measurably on which pseudorandom orbit supplies its randomness, even after marginal-statistics control.

  3. Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Removing explicit noise-level conditioning from graph diffusion models is often harmless, and the paper gives concentration and error-propagation bounds explaining why, with supporting experiments on QM9 and soc-Epinions1.

Pith tools