Pith Number

pith:GGWSAIGB

pith:2021:GGWSAIGBGVXMX4WGGWPUD4IG5Q

not attested not anchored not stored refs resolved

Improved Denoising Diffusion Probabilistic Models

Alex Nichol, Prafulla Dhariwal

Simple modifications let denoising diffusion models achieve competitive log-likelihoods while supporting much faster sampling.

arxiv:2102.09672 v1 · 2021-02-18 · cs.LG · cs.AI · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GGWSAIGBGVXMX4WGGWPUD4IG5Q}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We show that with a few simple modifications, DDPMs can also achieve competitive log-likelihoods while maintaining high sample quality. Additionally, we find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes with a negligible difference in sample quality.

C2weakest assumption

That the chosen modifications to the noise schedule and variance parameterization do not introduce unmeasured biases in the learned distribution or sampling dynamics beyond what the reported metrics capture.

C3one line summary

Targeted tweaks to DDPMs produce competitive likelihoods and high-quality samples, with learned reverse variances enabling 10x faster sampling and predictable scaling with compute.

References

17 extracted · 17 resolved · 3 Pith anchors

[1] Large Scale GAN Training for High Fidelity Natural Image Synthesis · arXiv:1809.11096

[2] Very deep vaes generalize autoregressive models and can outperform them on images 2011

[3] Gans trained by a two time-scale update rule converge to a local nash equilibrium 2017

[4] Flow++: Improving ﬂow-based generative models with variational dequantization and architecture design 1902 · arXiv:1902.00275

[5] Kynk¨a¨anniemi, T., Karras, T., Laine, S., Lehtinen, J., and Aila, T 2009

Formal links

2 machine-checked theorem links

Cited by

25 papers in Pith

Towards a Universal Foundation Model for Protein Dynamics: A Multi-Chain Tree-Structured Framework with Transformer Propagators

Exploring the flavor structure of leptons via diffusion models

Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions

Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment

Receipt and verification

First computed	2026-05-17T23:38:46.861530Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

31ad2020c1356ecbf2c6359f41f106ec3e6b985a5ee4f2c8ce30a67f3b5d4022

Aliases

arxiv: 2102.09672 · arxiv_version: 2102.09672v1 · doi: 10.48550/arxiv.2102.09672 · pith_short_12: GGWSAIGBGVXM · pith_short_16: GGWSAIGBGVXMX4WG · pith_short_8: GGWSAIGB

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/GGWSAIGBGVXMX4WGGWPUD4IG5Q \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 31ad2020c1356ecbf2c6359f41f106ec3e6b985a5ee4f2c8ce30a67f3b5d4022

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "084e01d0615c400d02aaa5f09cea919e3d7f0df92b7095fff0a7e29e81394683",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2021-02-18T23:44:17Z",
    "title_canon_sha256": "4e2dc29951e3f3625c1d250081314238ec51d711b56de8887f75705726de5415"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2102.09672",
    "kind": "arxiv",
    "version": 1
  }
}