Papers › Masked Diffusion Models Are Fast Distribution Learners

Masked Diffusion Models Are Fast Distribution Learners

20 Jun 2023arXiv:2306.11363archive 2025-07-28

Jiachen Lei, Qinglong Wang, Peng Cheng, Zhongjie Ba, Zhan Qin, Zhibo Wang, Zhenguang Liu, Kui Ren

Diffusion model has emerged as the de-facto model for image generation, yet the heavy training overhead hinders its broader adoption in the research community. We observe that diffusion models are commonly trained to learn all fine-grained visual information from scratch. This paradigm may cause unnecessary training costs hence requiring in-depth investigation. In this work, we show that it suffices to train a strong diffusion model by first pre-training the model to learn some primer distribution that loosely characterizes the unknown real image distribution. Then the pre-trained model can be fine-tuned for various generation tasks efficiently. In the pre-training stage, we propose to mask a high proportion (e.g., up to 90%) of input images to approximately represent the primer distribution and introduce a masked denoising score matching objective to train a model to denoise visible areas. In subsequent fine-tuning stage, we efficiently train diffusion model without masking. Utilizing the two-stage training framework, we achieves significant training acceleration and a new FID score record of 6.27 on CelebA-HQ 256 ×256 for ViT-based diffusion models. The generalizability of a pre-trained model further helps building models that perform better than ones trained from scratch on different downstream datasets. For instance, a diffusion model pre-trained on VGGFace2 attains a 46% quality improvement when fine-tuned on a different dataset that contains only 3000 images. Our code is available at https://github.com/jiachenlei/maskdm.

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 11 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 11 ran (9 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.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 11 samples that ran have no recorded date.

jiachenlei/maskdm officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 11 ran (2 instrument-failed) · 0 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.

Code Syntology ran Syntology

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
5ran

Licence: 0 of the 11 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 jiachenlei/maskdm. “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.

jiachenlei/maskdm official repository 11 samples, 11 ran (2 instrument-failed) · 0 unverified
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
utils/helper.py ran · honoured contract MIT (permissive) · 7f1040f5e3991d5e · report fixture: signature t:Tensor/2/float, args:tuple/1/Tensor, kwargs:dict/0/? · returned Tensor · level recorded, date not recorded
combine in 19 papers utils/config.py ran MIT (permissive) · 2a421bd3e3e98703 · report fixture: signature args:Namespace/0/?, config:dict/0/? · returned Namespace · level recorded 2026-09-26
cosine_beta_schedule in 76 papers gaussian_ddpm.py ran MIT (permissive) · 0bd8c65f1839edbf · report fixture: signature timesteps:int/0/int, s:float/0/float, shift:bool/0/bool, d:int/0/int · returned Tensor · level recorded 2026-09-26
default in 430 papers utils/helper.py ran · violated contract MIT (permissive) · d1ef6b8cb9a28a53 · report fixture: signature val:str/0/str, d:callable/0/? · returned str · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
utils/helper.py ran · violated contract MIT (permissive) · 608e364a9d2376a3 · report fixture: signature x:Tensor/1/int · returned bool · level recorded, date not recorded
get_sinusoid_encoding_table in 51 papers models/mask_uvit.py ran fingerprinted MIT (permissive) · 7dff50b3dd446750 · report fixture: signature n_position:int/0/int, d_hid:int/0/int · returned Tensor · level recorded 2026-09-26
linear_beta_schedule in 42 papers gaussian_ddpm.py ran · honoured contract fingerprinted MIT (permissive) · 482723f534770483 · report fixture: signature timesteps:int/0/int · returned Tensor · level recorded 2026-09-22
parse_yml utils/config.py ran fingerprinted MIT (permissive) · 5f118351f15bd3f6 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-26
patchify in 32 papers
census: 6 implementations from 8 papers, 6 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 4, kind float, dtype float32
models/mask_uvit.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 9cf076a2ae913f94 · report fixture: signature imgs:Tensor/4/float, patch_size:int/0/int · returned Tensor · level recorded, date not recorded
shuffle_along_axis datasets/masking_generator.py ran fingerprinted MIT (permissive) · ea28bd6049050f3b · report fixture: signature a:ndarray/3/float, axis:int/0/int · returned ndarray · level recorded 2026-09-26
timestep_embedding in 79 papers
census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind int, dtype int64
models/mask_uvit.py ran · our draft was wrong fingerprinted MIT (permissive) · b494dd297ded5960 · report fixture: signature timesteps:Tensor/1/int, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded, date not recorded

Tasks

DenoisingImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Denoising Score MatchingDiffusion

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