Papers › Score-Based Generative Modeling through Stochastic Differential Equations
Score-Based Generative Modeling through Stochastic Differential Equations
Yang song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution by slowly removing the noise. Crucially, the reverse-time SDE depends only on the time-dependent gradient field (\aka, score) of the perturbed data distribution. By leveraging advances in score-based generative modeling, we can accurately estimate these scores with neural networks, and use numerical SDE solvers to generate samples. We show that this framework encapsulates previous approaches in score-based generative modeling and diffusion probabilistic modeling, allowing for new sampling procedures and new modeling capabilities. In particular, we introduce a predictor-corrector framework to correct errors in the evolution of the discretized reverse-time SDE. We also derive an equivalent neural ODE that samples from the same distribution as the SDE, but additionally enables exact likelihood computation, and improved sampling efficiency. In addition, we provide a new way to solve inverse problems with score-based models, as demonstrated with experiments on class-conditional generation, image inpainting, and colorization. Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.89 and FID of 2.20, a competitive likelihood of 2.99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
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.
Syntology holds a reference implementation of neural ODE, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='neural ODE') (how to connect); the free check have('2011.13456') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2011.13456")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2011.13456", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2011.13456")
Code
Syntology 23 code samples harvested from 8 repositories linked to this paper: 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. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 7 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 16 samples from 7 repositories, 12 ran (6 with no instrument failure; 6 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 4 of its repositories that Syntology harvested for other papers:
- X-LANCE/VoiceFlow-TTS, community (archive-listed): harvested for another paper, listed under the repository
- claserken/SISS, community (archive-listed): harvested for another paper, listed under the repository
- ermongroup/ncsn, community (archive-listed): harvested for another paper, listed under the repository
- ermongroup/ncsnv2, community (archive-listed): harvested for another paper, listed under the repository
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. 2 of the 15 samples that ran have no recorded date.
15 repositories listed; official and paper-mentioned ones first.
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
23 samples harvested: 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. “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.
Licence: 4 of the 23 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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”. “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.
6f447a2b95b54845 · report
fixture: returned NoneCorrector · level recorded 2026-09-22 6fe4dbf5838e4df8 · report
fixture: returned NonePredictor · level recorded 2026-09-22 43fddf16d4b421ac · report
fixture: signature sde:MockSDE/0/?, model:MockModel/0/?, shape:tuple/1/int, predictor:NoneType/0/?, corrector:NoneType/0/?, inverse_scaler:callable/0/?, snr:float/0/float, n_steps:int/0/int, probability_flow:bool/0/bool, continuous:bool/0/bool, denoise:bool/0/bool, eps:float/0/float · returned function · level recorded 2026-09-22 0ef020b95f4bc102 · report
8a1938617d189156 · report
961b5bdb253bde68 · report
fixture: returned VariancePreservingSDE · level recorded 2026-09-22 559d174d6d82afd7 · report
fixture: returned VariancePreservingTruncatedSampling · level recorded 2026-09-22 4675c27602b677ef · report
fixture: signature shape:tuple/1/int, beta_min:float/0/float, beta_max:float/0/float, t_epsilon:float/0/float, T:float/0/float · returned Tensor · level recorded 2026-09-22 a255c2fd61329566 · report
fixture: signature sde:MockSDE/0/?, score_fn:callable/0/?, x:Tensor/4/float, t:Tensor/1/float · returned tuple · level recorded 2026-09-24 23c37bd71f8e0dbd · report
fixture: signature error:float/0/float · returned bool · level recorded 2026-09-24 0f41c312acba15d8 · report
fixture: signature x:Tensor/2/float · returned function · level recorded 2026-09-22 e79707d0454c79c9 · report
fixture: signature sigma_from:float/0/float, sigma_to:float/0/float, eta:float/0/float · returned tuple · level recorded 2026-09-22 dacabf6cda8ac542 · report
3f6adafb3e149eb3 · report
e3d0f1667dc4e323 · report
fixture: signature x:Tensor/4/float, t:Tensor/1/float, t_next:Tensor/1/float, et:Tensor/4/float, alphas_cump:Tensor/1/float · returned Tensor · level recorded 2026-09-22 8e6cd2ebb4cb3161 · report
fixture: signature x:Tensor/4/float, t_list:list/1/Tensor, model:callable/0/?, alphas_cump:Tensor/1/float, ets:list/1/empty · returned Tensor · level recorded 2026-09-22 c915fab99cb196da · report
fixture: signature model:callable/0/?, num_samples:int/0/int, input_dim:int/0/int, cond:Tensor/2/float, alphas_bar_sqrt:Tensor/1/float, one_minus_alphas_bar_sqrt:Tensor/1/float, betas:Tensor/1/float, num_steps:int/0/int, device:str/0/str · returned list · level recorded 2026-09-22 a05b1d0cf3f508b4 · report
fixture: signature cls:callable/0/?, name:NoneType/0/? · returned type · level recorded, date not recorded 473066ddf62a075a · report
fixture: signature cls:callable/0/?, name:NoneType/0/? · returned type · level recorded, date not recorded 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
8 assemblies on this paper: 7 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).
generated Assembly for neural ODE (graph method: neural ODE), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.
label matches by construction: the code was generated for this method (not judged by a model)
- corrector_step_ve entry · level 3 · ran · honoured contract ·
57f1014724a8920b1ff53e0cc8518f24f42f24bd893e67edea2f99f1dc6337fc
7 sibling assemblies for predictor-corrector framework (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- gen_order_2 entry · level 0 · unverified ·
61d75983e395ab02 - improved_eular sampler · level 0 · unverified ·
fe36f2c4259802ef - transfer helper · level 1 · ran · honoured contract ·
e3d0f1667dc4e323
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 9 bricks; individually on a fixture: 5 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; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- get_pc_sampler entry · level 1 · ran · our draft was wrong ·
43fddf16d4b421ac - shared_corrector_update_fn helper · level 0 · unverified ·
0ef020b95f4bc102 - shared_predictor_update_fn helper · level 0 · unverified ·
8a1938617d189156 - NoneCorrector helper · level 1 · ran ·
6f447a2b95b54845 - NonePredictor helper · level 1 · ran ·
6fe4dbf5838e4df8 - Corrector sampler · level 0 · unverified ·
b5b6009cef6e47d8 - register_corrector helper · level 1 · ran · our draft was wrong ·
a05b1d0cf3f508b4 - Predictor sampler · level 0 · unverified ·
fdabca225111e3dc - register_predictor helper · level 1 · ran · our draft was wrong ·
473066ddf62a075a
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 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 7 siblings
- EulerMaruayamaPredictor entry · level 1 · ran ·
a255c2fd61329566
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 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 7 siblings
- sample_from_diff entry · level 1 · ran · our draft was wrong ·
c915fab99cb196da
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 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 7 siblings
- VariancePreservingSDE entry · level 1 · ran ·
961b5bdb253bde68 - sample_vp_truncated_q helper · level 1 · ran · our draft was wrong ·
4675c27602b677ef - VariancePreservingTruncatedSampling helper · level 1 · ran ·
559d174d6d82afd7
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 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 7 siblings
- runge_kutta entry · level 1 · ran · our draft was wrong ·
8e6cd2ebb4cb3161 - transfer helper · level 1 · ran · honoured contract ·
e3d0f1667dc4e323
harvested Assembly for predictor-corrector framework (graph method: predictor-corrector framework). 5 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 7 siblings
- sample_dpm_adaptive entry · level 0 · unverified ·
3f6adafb3e149eb3 - DPMSolver sampler · level 0 · unverified ·
dacabf6cda8ac542 - PIDStepSizeController update_rule · level 1 · ran ·
23c37bd71f8e0dbd - default_noise_sampler helper · level 1 · ran · our draft was wrong ·
0f41c312acba15d8 - get_ancestral_step helper · level 1 · ran · honoured contract ·
e79707d0454c79c9
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="2011.13456") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Density Estimation | CIFAR-10 | score SDE | NLL (bits/dim) | 2.99 | #8 of 15 | 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
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