Papers › Mean Flows for One-step Generative Modeling

Mean Flows for One-step Generative Modeling

19 May 2025arXiv:2505.13447archive 2025-07-28

Zhengyang Geng, Mingyang Deng, Xingjian Bai, J. Zico Kolter, Kaiming He

We propose a principled and effective framework for one-step generative modeling. We introduce the notion of average velocity to characterize flow fields, in contrast to instantaneous velocity modeled by Flow Matching methods. A well-defined identity between average and instantaneous velocities is derived and used to guide neural network training. Our method, termed the MeanFlow model, is self-contained and requires no pre-training, distillation, or curriculum learning. MeanFlow demonstrates strong empirical performance: it achieves an FID of 3.43 with a single function evaluation (1-NFE) on ImageNet 256x256 trained from scratch, significantly outperforming previous state-of-the-art one-step diffusion/flow models. Our study substantially narrows the gap between one-step diffusion/flow models and their multi-step predecessors, and we hope it will motivate future research to revisit the foundations of these powerful models.

PaperPDFCodeCode Syntology ran

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

Syntology 12 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 2 repositories, 9 ran (7 with no instrument failure; 2 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Gsunshine/meanflow mentioned on GitHubjaxSyntology: 1 sample, 0 ran · 1 unverified report
ali-vilab/FACM mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Flow-Anchored Consistency Models (arXiv:2507.03738; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
andypinxinliu/GestureLSM mentioned on GitHubpytorchMITSyntology: 11 samples, 9 ran (2 instrument-failed) · 2 unverified 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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
7ran
3unverified

Licence: 0 of the 12 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 2 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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Gsunshine/meanflow community (archive-listed) 1 sample, 0 ran · 1 unverified
generate in 143 papers
census: 5 implementations from 6 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
meanflow.py unverified MIT (permissive) · 15cb9cb0de4aadad · report
andypinxinliu/GestureLSM community (archive-listed) 11 samples, 9 ran (2 instrument-failed) · 2 unverified
exponential_pdf models/LSM.py ran MIT (permissive) · f3c44f47824302dc · report fixture: signature x:ndarray/1/float, a:ndarray/0/float · returned ndarray · level recorded 2026-09-25
find_attention_modules models/MeanFlow.py ran MIT (permissive) · 1b12f7f17b973eee · report fixture: signature module:callable/0/?, attention_modules:NoneType/0/? · returned list · level recorded 2026-09-25
get_loss_func in 26 papers optimizers/loss_factory.py ran · our draft was wrong MIT (permissive) · 4f043bf1bec12652 · report fixture: signature loss_name:str/0/str, beta:float/0/float, reduction:str/0/str · returned HuberLoss · level recorded 2026-09-24
get_module_config in 5 papers models/config.py ran MIT (permissive) · 2057a8b48b0d5cf3 · report fixture: signature cfg_model:DictConfig/0/?, paths:list/1/str, cfg_root:str/0/str · returned DictConfig · level recorded 2026-09-25
get_obj_from_str in 52 papers models/config.py ran MIT (permissive) · 6f951d437f9f5c5f · report fixture: signature string:str/0/str, reload:bool/0/bool · returned type · level recorded 2026-09-25
mean_flat in 53 papers
census: 9 implementations from 18 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 4, kind float, dtype float32
models/MeanFlow.py ran · our draft was wrong fingerprinted MIT (permissive) · dd96bc6c07c85dae · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
sample_beta_distribution models/LSM.py ran MIT (permissive) · 1ba44760ad133e99 · report fixture: signature num_samples:int/0/int, alpha:float/0/float, beta:float/0/float, t_min:float/0/float, t_max:float/0/float · returned Tensor · level recorded 2026-09-25
sample_t models/LSM.py ran MIT (permissive) · f9b3244bb6e382cd · report fixture: signature exponential_pdf:MockExponentialPDF/0/?, num_samples:int/0/int, a:int/0/int · returned Tensor · level recorded 2026-09-25
update_lr_warm_up rvq_beatx_train.py ran MIT (permissive) · b3786bbc856619f6 · report fixture: signature optimizer:SGD/0/?, nb_iter:int/0/int, warm_up_iter:int/0/int, lr:float/0/float · returned tuple · level recorded 2026-09-25
instantiate_from_config in 47 papers models/config.py unverified MIT (permissive) · 16e41676220876a4 · report
reshape_coefs models/MeanFlow.py unverified MIT (permissive) · 24486901843b5f5c · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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