---
title: "Denoising Diffusion Probabilistic Models"
description: "Denoising Diffusion Probabilistic Models turns generation into a sequence of small denoising steps. Read it to connect variational learning, Gaussian noise, and score matching to the practical recipe that became the foundation of modern diffusion image models."
canonical_url: "https://fanout.sh/daily/2026-07-25-denoising-diffusion-probabilistic-models"
md_url: "https://fanout.sh/daily/2026-07-25-denoising-diffusion-probabilistic-models.md"
last_updated: "2026-07-25"
access: "public"
---

# Denoising Diffusion Probabilistic Models

Denoising Diffusion Probabilistic Models turns generation into a sequence of small denoising steps. Read it to connect variational learning, Gaussian noise, and score matching to the practical recipe that became the foundation of modern diffusion image models.

## Paper details

- Authors: Ho, Jain, and Abbeel

- Venue: NeurIPS 2020

- Track: ML Math

- Difficulty: Medium

- Reading time: 50 min

- Original paper: https://arxiv.org/abs/2006.11239

## What you will learn

- How a fixed forward Markov process gradually turns data into Gaussian noise.

- How a learned reverse process generates samples by predicting and removing noise one step at a time.

- Why the variational bound and its connection to denoising score matching lead to a simple noise-prediction training objective.

## Continue exploring

[Explore Diffusion Models](https://fanout.sh/knowledge-graph?node=ai-research%3Aconcept%3Adiffusion-model): Open Fanout's diffusion-model concept node and connect the paper to denoising, score matching, latent variables, and iterative generation.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md