Papers › Generative Modeling by Estimating Gradients of the Data Distribution

Generative Modeling by Estimating Gradients of the Data Distribution

12 Jul 2019NeurIPS 2019 12arXiv:1907.05600archive 2025-07-28

Yang Song, Stefano Ermon

We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores, i.e., the vector fields of gradients of the perturbed data distribution for all noise levels. For sampling, we propose an annealed Langevin dynamics where we use gradients corresponding to gradually decreasing noise levels as the sampling process gets closer to the data manifold. Our framework allows flexible model architectures, requires no sampling during training or the use of adversarial methods, and provides a learning objective that can be used for principled model comparisons. Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (ermongroup/ncsn) is linked to this paper; the 22 samples below come from 8 community repositories. Syntology harvested code from ermongroup/ncsn for another paper.

ermongroup/ncsn: Syntology's graph links these samples to Estimating High Order Gradients of the Data Distribution by Denoising (arXiv:2111.04726; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 22 code samples harvested from 8 repositories linked to this paper: 14 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 22 samples from 8 repositories, 14 ran (11 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

13 repositories listed; official and paper-mentioned ones first.

ermongroup/ncsn officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Estimating High Order Gradients of the Data Distribution by Denoising (arXiv:2111.04726; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Lornatang/PyTorch-NCSN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
PeterZhizhin/HSE-DeepLearning-NCSN mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
Xemnas0/NCSN-TF2.0 mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ermongroup/ncsnv2 mentioned on GitHubpytorchSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
guillaumeboniface/super_resolution mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
henryaddison/score_sde_pytorch mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Machine learning emulation of a local-scale UK climate model (arXiv:2211.16116; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
mbordyuh/score_matching mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
voxmenthe/ncsn_1 mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
xiwei-cheng/chained_ld mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
yang-song/score_sde mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Score-Based Generative Modeling through Stochastic Differential Equations (arXiv:2011.13456; that paper's own run record: 15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
yang-song/score_sde_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
soran-ghaderi/torchebm pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

22 samples harvested: 14 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
10ran
8unverified

Licence: 9 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 8 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Lornatang/PyTorch-NCSN community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Score in 6 papers models/scorenet.py ran Apache-2.0 (permissive) · 04ab830c8352fa59 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
PeterZhizhin/HSE-DeepLearning-NCSN community (archive-listed) 2 samples, 0 ran · 2 unverified
ToyExperimentDataset langevin.py unverified GPL-3.0 (copyleft) · pointer only · 45b72aead272b1d0 · report
anneal_langevin langevin.py unverified GPL-3.0 (copyleft) · pointer only · 4208709a6798c6ab · report
Xemnas0/NCSN-TF2.0 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
dsm_loss losses/losses.py ran; the contract check could not run (RAISES) no licence file found · pointer only · cff1bdc3f34eb185 · report fixture: signature score:EagerTensor/4/float, x_perturbed:EagerTensor/4/float, x:EagerTensor/4/float, sigmas:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
ermongroup/ncsnv2 community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
ConditionalBatchNorm2d models/ncsnv2.py ran · metamorphic tier: deterministic MIT (permissive) · a36c0d3f631164cf · report fixture: returned ConditionalBatchNorm2d · level recorded 2026-09-22
ConditionalInstanceNorm2d models/ncsnv2.py ran · metamorphic tier: deterministic MIT (permissive) · b67d9759d330f8e9 · report fixture: returned ConditionalInstanceNorm2d · level recorded 2026-09-22
ConditionalInstanceNorm2dPlus models/ncsnv2.py ran · metamorphic tier: deterministic MIT (permissive) · 543e9573790e3f36 · report fixture: returned ConditionalInstanceNorm2dPlus · level recorded 2026-09-22
ConditionalNoneNorm2d models/ncsnv2.py ran · metamorphic tier: deterministic MIT (permissive) · 28b6b8fdea88c99d · report fixture: returned ConditionalNoneNorm2d · level recorded 2026-09-22
InstanceNorm2dPlus models/ncsnv2.py ran · metamorphic tier: deterministic MIT (permissive) · d217a4b1f1925355 · report fixture: returned InstanceNorm2dPlus · level recorded 2026-09-22
NoneNorm2d models/ncsnv2.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f02dfb63731445ee · report fixture: returned NoneNorm2d · level recorded 2026-09-22
VarianceNorm2d models/ncsnv2.py ran · metamorphic tier: deterministic MIT (permissive) · 2ceaba81d90f5640 · report fixture: returned VarianceNorm2d · level recorded 2026-09-22
get_sigmas in 10 papers models/ncsnv2.py ran · honoured contract MIT (permissive) · 308c9ffe9425921a · report fixture: signature config:Config/0/? · returned Tensor · level recorded 2026-09-22
ConditionalVarianceNorm2d models/ncsnv2.py unverified MIT (permissive) · 2985c25add4b01dc · report
NCSNv2 models/ncsnv2.py unverified MIT (permissive) · 9979dc271f83e97a · report
get_normalization in 25 papers models/ncsnv2.py unverified MIT (permissive) · c0db9b95b0194d7a · report
guillaumeboniface/super_resolution community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
generate_noisy_image_batch sr3/noise_utils.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 7c385bfdbcac9ebc · report fixture: signature image:EagerTensor/4/float, noise_param:EagerTensor/1/float · returned tuple · level recorded 2026-09-22
mbordyuh/score_matching community (archive-listed) 2 samples, 0 ran · 2 unverified
jacobian in 21 papers model.py unverified no licence file found · pointer only · 1a2134b893169239 · report
score_matching model.py unverified no licence file found · pointer only · 9a46fa84765de343 · report
xiwei-cheng/chained_ld community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
ResNetScore models/scorenet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 55fdb754c0cda85c · report fixture: returned ResNetScore · level recorded 2026-09-22
ResnetBlock in 49 papers models/scorenet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 495f6791fda7d15e · report fixture: returned ResnetBlock · level recorded 2026-09-22
get_norm_layer in 111 papers models/scorenet.py ran · our draft was wrong no licence file found · pointer only · 05f3653dd76468d9 · report fixture: signature norm_type:str/0/str · returned partial · level recorded 2026-09-22
yang-song/score_sde_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
SDE in 8 papers sde_lib.py unverified Apache-2.0 (permissive) · 2149b8836f88ca16 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

8 sibling assemblies for Generative Modeling by Estimating Gradients of the Data Distribution (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 11 bricks; individually on a fixture: 8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. NCSNv2 entry · level 0 · unverified · 9979dc271f83e97a
  2. get_normalization helper · level 0 · unverified · c0db9b95b0194d7a
  3. get_sigmas helper · level 1 · ran · honoured contract · 308c9ffe9425921a
  4. ConditionalBatchNorm2d helper · level 1 · ran · a36c0d3f631164cf
  5. ConditionalInstanceNorm2d helper · level 1 · ran · b67d9759d330f8e9
  6. ConditionalInstanceNorm2dPlus helper · level 1 · ran · 543e9573790e3f36
  7. ConditionalNoneNorm2d helper · level 1 · ran · 28b6b8fdea88c99d
  8. ConditionalVarianceNorm2d helper · level 0 · unverified · 2985c25add4b01dc
  9. InstanceNorm2dPlus helper · level 1 · ran · d217a4b1f1925355
  10. NoneNorm2d helper · level 1 · ran · f02dfb63731445ee
  11. VarianceNorm2d helper · level 1 · ran · 2ceaba81d90f5640

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. dsm_loss entry · level 1 · ran; the contract check could not run (RAISES) · cff1bdc3f34eb185

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. score_matching entry · level 0 · unverified · 9a46fa84765de343
  2. jacobian helper · level 0 · unverified · 1a2134b893169239

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. ResNetScore entry · level 1 · ran · 55fdb754c0cda85c
  2. ResnetBlock helper · level 1 · ran · 495f6791fda7d15e
  3. get_norm_layer helper · level 1 · ran · our draft was wrong · 05f3653dd76468d9

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. generate_noisy_image_batch entry · level 1 · ran; the contract check could not run (RAISES) · 7c385bfdbcac9ebc

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. anneal_langevin entry · level 0 · unverified · 4208709a6798c6ab
  2. ToyExperimentDataset helper · level 0 · unverified · 45b72aead272b1d0

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. Score entry · level 1 · ran · 04ab830c8352fa59

harvested Assembly for Generative Modeling by Estimating Gradients of the Data Distribution (graph method: Generative Modeling by Estimating Gradients of the Data Distribution). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. SDE entry · level 0 · unverified · 2149b8836f88ca16

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1907.05600") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationImage Inpainting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CIFAR-10 NCSN FID 25.32 #63 of 78 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Denoising Score Matching

Denoising Score Matching

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections